© 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. 12-TRANSCODER-HP
    7. 22009
    Prev
    Next
    INDEX
    Explanations

    Unstructured text or data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    å¡Ĭ
    -0.28
    åŁļ
    -0.27
    /Instruction
    -0.27
     plate
    -0.25
    æĢ»å±Ģ
    -0.24
    æŶéĹ´æ®µ
    -0.24
    åĿĹ
    -0.23
    èĥĮ
    -0.23
     Rut
    -0.23
    ategori
    -0.23
    POSITIVE LOGITS
    她æĺ¯
    0.27
    严
    0.25
    AsyncResult
    0.25
    æĺ¯åĽ½åĨħ
    0.25
    (([
    0.24
    oust
    0.24
    본
    0.23
    åĴĮåıijå±ķ
    0.23
    å½ĵ代
    0.23
    æijĦ
    0.23
    Activations Density 0.002%

    No Known Activations