© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 54405
    Prev
    Next
    INDEX
    Explanations

    eigen

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _stdio
    -0.29
    å¤ıåŃ£
    -0.29
    湿
    -0.28
     teenage
    -0.28
     old
    -0.27
     Ä°nsan
    -0.26
    大éĩı
    -0.26
     meisten
    -0.26
    ç¾İ丽
    -0.26
    åĨ¬åŃ£
    -0.26
    POSITIVE LOGITS
     packet
    0.28
     period
    0.28
     projection
    0.28
     sublist
    0.27
    board
    0.27
     hub
    0.27
     schematic
    0.27
    room
    0.27
     hookup
    0.27
     inquiry
    0.27
    Activations Density 0.036%

    No Known Activations