© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 31-TRANSCODER-HP
    7. 17851
    Prev
    Next
    INDEX
    Explanations

    random technical text

    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
    Negative Logits
    edList
    -0.33
     ride
    -0.29
    ê·Ģ
    -0.28
    ades
    -0.27
    ions
    -0.27
     Kis
    -0.26
    ED
    -0.26
    ul
    -0.26
    edad
    -0.25
    edBy
    -0.25
    POSITIVE LOGITS
    æª
    0.25
    tera
    0.25
    lator
    0.24
    æ¦ľ
    0.24
     slump
    0.24
    yne
    0.24
    nid
    0.24
    ä¹Łå¸ĮæľĽ
    0.24
    æĪĺçķ¥å¸ĥå±Ģ
    0.23
     duke
    0.23
    Activations Density 0.006%

    No Known Activations