© 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. 22-TRANSCODER-HP
    7. 113029
    Prev
    Next
    INDEX
    Explanations

    news/reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    opoulos
    -0.33
    adera
    -0.31
     Shop
    -0.26
    -opacity
    -0.24
     simulated
    -0.24
    å¤įåIJĪ
    -0.24
    aron
    -0.24
    akash
    -0.24
    -major
    -0.24
    licit
    -0.24
    POSITIVE LOGITS
    ANA
    0.26
    åıĺäºĨ
    0.25
    pike
    0.25
    æĿ¥ä¸įåıĬ
    0.24
    çݩ家
    0.24
    QUE
    0.24
    ä¸Ģ大åłĨ
    0.23
     Dra
    0.23
     Already
    0.23
     em
    0.23
    Activations Density 0.006%

    No Known Activations