© 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. 21934
    Prev
    Next
    INDEX
    Explanations

    infected

    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
     Transportation
    -0.26
    gow
    -0.25
     Gab
    -0.25
    razy
    -0.25
    bere
    -0.25
     Alive
    -0.24
    htable
    -0.24
    quot
    -0.24
    gom
    -0.24
    ä¼ŀ
    -0.24
    POSITIVE LOGITS
    uter
    0.28
    åĻ¨
    0.28
    æķĪåĬĽ
    0.27
     desp
    0.26
    ç¼ĸ
    0.26
     ник
    0.26
     compiled
    0.26
    electron
    0.25
    lard
    0.25
    ä¼ļ议精ç¥ŀ
    0.25
    Activations Density 0.000%

    No Known Activations