© 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. 3994
    Prev
    Next
    INDEX
    Explanations

    return value

    np_max-act · gemini-2.0-flash

    mentions of a function or method’s return value or return type in programming contexts.

    oai_token-act-pair · gpt-5Triggered 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
    .Cond
    -0.07
     usize
    -0.07
    onesia
    -0.07
     onData
    -0.06
    dess
    -0.06
     POST
    -0.06
     PRO
    -0.06
     Kon
    -0.06
    valid
    -0.06
    constant
    -0.06
    POSITIVE LOGITS
    第三方
    0.07
    ('+
    0.07
     Launcher
    0.07
    ᶻ
    0.07
    -buffer
    0.07
    规划设计
    0.06
    ythe
    0.06
     assassin
    0.06
     Elon
    0.06
    	fclose
    0.06
    Activations Density 0.010%

    No Known Activations