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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 19-RESID-POST-AA
    11. 89445
    Prev
    Next
    INDEX
    Explanations

    say 'asked' or 'from'

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    青岛
    -0.07
    DEL
    -0.07
    ////////////////////////////////////////////////////////////////////////
    -0.07
    -choice
    -0.07
    Tcp
    -0.07
    Bg
    -0.07
    /ion
    -0.07
    Quantity
    -0.06
    Recursive
    -0.06
    gger
    -0.06
    POSITIVE LOGITS
     לפעמים
    0.08
    ropri
    0.07
    综合利用
    0.07
    _draft
    0.07
    现状
    0.07
    ungkin
    0.06
     playable
    0.06
    周
    0.06
    (lhs
    0.06
    可靠
    0.06
    Activations Density 0.001%

    No Known Activations