© 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. 19519
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     discharge
    -0.31
     grow
    -0.31
    ä¾Ŀ
    -0.28
     depend
    -0.27
    stituição
    -0.27
    zia
    -0.26
    ury
    -0.26
    gue
    -0.26
     weren
    -0.26
    ç¶ļãģĦãģ¦
    -0.26
    POSITIVE LOGITS
     is
    0.40
     Cone
    0.28
     vá»±c
    0.27
    igits
    0.26
    imen
    0.25
     Sachs
    0.25
    ore
    0.25
     scars
    0.25
    s
    0.25
    æĺ¯
    0.24
    Activations Density 6.871%

    No Known Activations