© 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. 22-TRANSCODER-HP
    7. 86841
    Prev
    Next
    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æıIJä¾Ľä¼ĺè´¨
    -0.31
    ropriate
    -0.26
    åĽłä¸ºæĪij们
    -0.26
    æIJŀ好
    -0.25
    .TypeOf
    -0.25
    coc
    -0.25
     epith
    -0.25
    ilm
    -0.25
    ãģªãĤĭ
    -0.24
    ä¸ĵåįĸ
    -0.24
    POSITIVE LOGITS
    ureka
    0.27
    uncio
    0.26
    ÑģÑĤи
    0.26
    åı£æ°Ķ
    0.25
    кли
    0.25
    Sdk
    0.24
    趣
    0.24
    ç¥Ł
    0.24
    aby
    0.24
    Slim
    0.24
    Activations Density 0.040%

    No Known Activations