© 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. 18155
    Prev
    Next
    INDEX
    Explanations

    work

    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
     virtual
    -0.36
    virtual
    -0.36
    èĻļæĭŁ
    -0.30
     Virtual
    -0.28
    Virtual
    -0.27
    ترÙĨت
    -0.27
    offline
    -0.27
    .virtual
    -0.26
    ä¸Ĭä¼ł
    -0.26
     reporting
    -0.25
    POSITIVE LOGITS
     Working
    0.39
     working
    0.35
    å·¥ä½ľ
    0.35
    Working
    0.34
     worked
    0.32
     work
    0.31
    working
    0.31
     Work
    0.31
     works
    0.30
     WORK
    0.30
    Activations Density 1.921%

    No Known Activations