© 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. 18435
    Prev
    Next
    INDEX
    Explanations

    )

    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
    ↵ ↵
    -0.56
    ↵	↵
    -0.54
    &nbsp
    -0.54
    ↵		↵
    -0.50
    \n
    -0.50
    ï¼ĮåĪĻ
    -0.49
    <br
    -0.48
    ↵↵
    -0.48
    ↵  ↵
    -0.47
    <strong
    -0.46
    POSITIVE LOGITS
    ãĢģ“
    0.37
    __',
    0.29
    ’,
    0.28
    !',
    0.26
     The
    0.26
    çī¹åĪ«æĺ¯
    0.26
    !",
    0.26
     This
    0.25
     According
    0.25
    %↵
    0.25
    Activations Density 50.813%

    No Known Activations