© 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. 30129
    Prev
    Next
    INDEX
    Explanations

    code/programming

    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
    Not in Any Lists

    No Comments

    Negative Logits
    个å¤ļ
    -0.34
    è¿Ļä¸ĢçĤ¹
    -0.29
    à¤ł
    -0.29
    eturn
    -0.26
     princip
    -0.25
    æį¢
    -0.25
    llen
    -0.24
     >>↵↵
    -0.24
    è¿ĻäºĽéĹ®é¢ĺ
    -0.24
    ...]↵↵
    -0.23
    POSITIVE LOGITS
    Dlg
    0.26
    ãģĹãĤĥ
    0.25
     SAS
    0.24
    ä¼ĺç¾İ
    0.24
    dlg
    0.24
     axial
    0.24
    ides
    0.24
    olar
    0.23
     /*#__
    0.23
    gü
    0.23
    Activations Density 0.506%

    No Known Activations