© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 80051
    Prev
    Next
    INDEX
    Explanations

    Right parentheses/brackets

    np_max-act · gemini-2.0-flash

    the ends of command substitutions or subshell expressions (tokens like '")' and '))' that close $(...) or $((...))).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Get
    -0.07
    /O
    -0.07
    ://
    -0.07
    ',(
    -0.07
    *(
    -0.07
     notation
    -0.07
     stimulus
    -0.07
     Kathleen
    -0.07
    Ⱏ
    -0.07
    .");↵↵
    -0.07
    POSITIVE LOGITS
    멱
    0.07
    -monitor
    0.07
    _glob
    0.07
    mó
    0.07
    ,
    0.07
    sei
    0.07
    Warn
    0.06
     descripcion
    0.06
    .mp
    0.06
    穿上
    0.06
    Activations Density 0.100%

    No Known Activations