© 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. 8171
    Prev
    Next
    INDEX
    Explanations

    of

    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
    (jButton
    -0.07
     provides
    -0.07
    סו
    -0.07
    /renderer
    -0.07
    есь
    -0.07
     Prescott
    -0.06
    三是
    -0.06
     sine
    -0.06
     cosine
    -0.06
     hôn
    -0.06
    POSITIVE LOGITS
    Integer
    0.08
    .port
    0.08
     cardboard
    0.07
     WEEK
    0.07
    PRINT
    0.07
    ระยะ
    0.07
    _store
    0.07
    列为
    0.07
     woes
    0.06
    _VISIBLE
    0.06
    Activations Density 0.018%

    No Known Activations