© 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. 24059
    Prev
    Next
    INDEX
    Explanations

    %-

    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
    æ´½
    -0.27
    åīĤéĩı
    -0.26
    åįķä»·
    -0.25
    ~~~~~~~~
    -0.24
    çĸı
    -0.24
    æĹ¥æĬ¥éģĵ
    -0.24
     ***↵
    -0.23
    ichtet
    -0.23
     Collider
    -0.23
    esty
    -0.23
    POSITIVE LOGITS
     slur
    0.28
    Äįe
    0.26
    cers
    0.26
    ills
    0.26
     deton
    0.25
    é¢į
    0.24
    eri
    0.24
    ç»ĵæĿŁåIJİ
    0.24
    ercul
    0.24
    erie
    0.24
    Activations Density 0.000%

    No Known Activations