© 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. 30-TRANSCODER-HP
    7. 97039
    Prev
    Next
    INDEX
    Explanations

    Code and reports

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Seam
    -0.31
     habit
    -0.26
    å¥ĩå¦Ļ
    -0.25
     IActionResult
    -0.24
    è·¨å¢ĥ
    -0.24
    -css
    -0.24
    AsStream
    -0.23
    ç»ĵæŀĦè°ĥæķ´
    -0.23
    æī¶è´«å·¥ä½ľ
    -0.23
    ÑĦик
    -0.23
    POSITIVE LOGITS
    åİĭ
    0.26
    ãĥĸãĥ©
    0.25
    зв
    0.25
    onus
    0.25
     atr
    0.25
    ç¿Ĭ
    0.24
     dipl
    0.24
     suspension
    0.24
    ìľĦ
    0.24
    Pressure
    0.24
    Activations Density 0.015%

    No Known Activations