© 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. 18331
    Prev
    Next
    INDEX
    Explanations

    special characters

    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
     Koch
    -0.26
    >{"
    -0.26
    imap
    -0.25
    utto
    -0.25
    hang
    -0.24
    inar
    -0.24
    æĮĩçĤ¹
    -0.23
    çŀĮ
    -0.23
    HEME
    -0.23
    hi
    -0.23
    POSITIVE LOGITS
     @(
    0.46
    @(
    0.40
     ${(
    0.36
    {(
    0.35
    /(
    0.32
     $(
    0.31
     {(
    0.31
     }(
    0.31
    ä¸ŃåĽ½äºº
    0.30
    <=(
    0.29
    Activations Density 10.521%

    No Known Activations