© 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. 18857
    Prev
    Next
    INDEX
    Explanations

    computer code

    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
    辩
    -0.28
    *X
    -0.28
    upal
    -0.27
    è¾ľ
    -0.27
    çĸ
    -0.27
    _X
    -0.26
     X
    -0.26
    MET
    -0.26
    me
    -0.25
    çݰ代åĮĸ
    -0.24
    POSITIVE LOGITS
    	Runtime
    0.28
     pu
    0.28
    intree
    0.27
    /Runtime
    0.27
    æ¡ĵ
    0.26
    èĥ½åĬĽ
    0.25
    chers
    0.25
    .capacity
    0.24
    .Loader
    0.23
    .pivot
    0.23
    Activations Density 0.129%

    No Known Activations