© 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. 29357
    Prev
    Next
    INDEX
    Explanations

    Lack of control/explanation

    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
    ivia
    -0.31
    asons
    -0.27
    etu
    -0.27
    //}↵
    -0.26
    blade
    -0.24
    ç»ıéªĮåĢ¼
    -0.24
    éĨª
    -0.24
    wor
    -0.24
     autoload
    -0.24
    ık
    -0.23
    POSITIVE LOGITS
    å¼Ģ
    0.28
    åĮħ容
    0.26
    ç»ĩ
    0.26
     fence
    0.26
    æ¯ģçģŃ
    0.25
    ä¸ĢåIJ¬
    0.25
     covering
    0.24
    map
    0.24
    ↵↵
    0.24
    人æŃ»äº¡
    0.24
    Activations Density 1.210%

    No Known Activations