© 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. 33-TRANSCODER-HP
    7. 52675
    Prev
    Next
    INDEX
    Explanations

    United

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    iese
    -0.29
    idas
    -0.29
    Fine
    -0.25
     sca
    -0.25
    è´¨
    -0.24
    sect
    -0.24
    妨
    -0.24
     New
    -0.24
    fähig
    -0.23
    M
    -0.23
    POSITIVE LOGITS
     //~
    0.28
    ä¹Łä¸įæĥ³
    0.27
    è§īå¾Ĺèĩªå·±
    0.26
    qid
    0.25
    roys
    0.25
    -th
    0.25
    æį¢äºĨ
    0.24
    ç»Ħç»ĩå®ŀæĸ½
    0.24
    æīĢ说
    0.23
     attest
    0.23
    Activations Density 0.025%

    No Known Activations