© 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. 22141
    Prev
    Next
    INDEX
    Explanations

    breakfast

    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
    代表çĿĢ
    -0.27
    çīĩéĿ¢
    -0.26
    ("-");↵
    -0.25
     prem
    -0.25
     neut
    -0.24
     {}).
    -0.24
    ancements
    -0.24
     Cousins
    -0.24
    åĩłæŃ¥
    -0.24
    ë³ij
    -0.24
    POSITIVE LOGITS
     kob
    0.29
    apult
    0.25
     zaj
    0.25
    .lesson
    0.25
     Portug
    0.24
    еÑĢиал
    0.24
    é²Ģ
    0.24
    unately
    0.24
    _Info
    0.24
    argc
    0.23
    Activations Density 0.016%

    No Known Activations