© 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. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 111962
    Prev
    Next
    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    äºĨä¸Ģæī¹
    -0.29
    -night
    -0.27
    subst
    -0.26
    æıIJåįĩäºĨ
    -0.26
    night
    -0.26
    mouth
    -0.26
    å¿ħä¸įåı¯
    -0.26
    effect
    -0.25
     indict
    -0.25
     negot
    -0.24
    POSITIVE LOGITS
    dek
    0.27
    _href
    0.26
    DATABASE
    0.25
     **)&
    0.25
    å¼ºåĽ½
    0.24
    åĽ¾çīĩæĿ¥æºIJ
    0.24
    á»ĩu
    0.24
     Pics
    0.24
     dur
    0.24
    ptune
    0.24
    Activations Density 0.019%

    No Known Activations