Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 13947
    Prev
    Next
    INDEX
    Explanations

    function (programming)

    np_max-act · gemini-2.0-flash
    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
     jButton
    -0.09
    那
    -0.07
    apest
    -0.07
    夕
    -0.07
    เลย
    -0.06
    목
    -0.06
    תוכן
    -0.06
     était
    -0.06
     obligation
    -0.06
     exerc
    -0.06
    POSITIVE LOGITS
     Eyes
    0.08
     restroom
    0.07
    Civil
    0.07
    _SAMPL
    0.07
    Queryable
    0.07
    SCII
    0.07
     Caught
    0.07
     Wonder
    0.07
     Haz
    0.07
    brush
    0.07
    Activations Density 0.029%

    No Known Activations