© 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. 9-TRANSCODER-HP
    7. 30459
    Prev
    Next
    INDEX
    Explanations

    bury

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Noon
    -0.26
    AILS
    -0.26
    omi
    -0.26
     habil
    -0.26
    æīįåı¯ä»¥
    -0.25
    é¡»
    -0.25
    á»ĵn
    -0.25
    çĪ¸
    -0.25
    åºŁçī©
    -0.25
    缸éĢļ
    -0.25
    POSITIVE LOGITS
    缸
    0.28
    DataRow
    0.27
    pread
    0.26
     anonymity
    0.26
     mapStateToProps
    0.25
    æ±Łå±±
    0.24
    èŁĨ
    0.24
     Dry
    0.23
    erver
    0.23
    brace
    0.23
    Activations Density 0.112%

    No Known Activations