© 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. 35-TRANSCODER-HP
    7. 40575
    Prev
    Next
    INDEX
    Explanations

    mixed languages, code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     is
    -0.46
     will
    -0.38
     can
    -0.38
     has
    -0.38
     are
    -0.37
     could
    -0.34
     would
    -0.33
     were
    -0.33
     it
    -0.32
     was
    -0.31
    POSITIVE LOGITS
    åĴĮ
    0.46
    åĴĮåıijå±ķ
    0.33
     and
    0.33
    and
    0.33
     vÃł
    0.31
    åĴĮä»ĸçļĦ
    0.30
    åĴĮæĶ¯æĮģ
    0.30
    åĴĮæľįåĬ¡
    0.30
     и
    0.29
    è¿ĺ好
    0.29
    Activations Density 3.913%

    No Known Activations