© 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. 31-TRANSCODER-HP
    7. 18965
    Prev
    Next
    INDEX
    Explanations

    decision, determination

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atic
    -0.33
     phased
    -0.27
    éĥ¨
    -0.26
     {}:
    -0.26
     Sandwich
    -0.26
    顺
    -0.25
    éĹŃçݯ
    -0.25
    åĨ¢
    -0.24
     Benson
    -0.24
    batim
    -0.24
    POSITIVE LOGITS
    кÑĤ
    0.27
     tÃł
    0.26
     GTX
    0.26
    OnError
    0.26
     OnTriggerEnter
    0.25
     tg
    0.25
    theses
    0.24
    fähig
    0.24
    å·¥ç¨ĭæĸ½å·¥
    0.24
     XT
    0.24
    Activations Density 0.003%

    No Known Activations