© 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. 22116
    Prev
    Next
    INDEX
    Explanations

    Legal/formal documents

    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
     Witness
    -0.28
    å¼Ĥè®®
    -0.27
    elp
    -0.27
     verz
    -0.26
    æµģ
    -0.25
     Uncomment
    -0.25
    ection
    -0.25
     tracker
    -0.25
    _observer
    -0.24
    åĺĺ
    -0.24
    POSITIVE LOGITS
    bsites
    0.28
    -slot
    0.26
    åĪĩæĪIJ
    0.26
    çķª
    0.26
    æĽ´æ·±
    0.24
    fab
    0.24
    Slot
    0.23
     Slots
    0.23
    æĢģ
    0.23
    çģ¯ç¬¼
    0.23
    Activations Density 0.001%

    No Known Activations