© 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. 21992
    Prev
    Next
    INDEX
    Explanations

    programming, software development contexts

    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
    oad
    -0.28
     dang
    -0.27
    owie
    -0.26
    åŃ©
    -0.26
    owy
    -0.26
    té
    -0.26
    çļĦåIJĦç§į
    -0.25
    év
    -0.24
     graphs
    -0.24
    ureen
    -0.24
    POSITIVE LOGITS
    erson
    0.30
    éħĬ
    0.27
    oley
    0.26
     Raiders
    0.26
     coordinated
    0.26
    daily
    0.25
    åij¨äºĮ
    0.25
    æĮ¯å¥ĭ
    0.24
    yat
    0.24
     endian
    0.23
    Activations Density 0.000%

    No Known Activations