© 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. 29238
    Prev
    Next
    INDEX
    Explanations

    is

    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
    èįĩ
    -0.30
    eton
    -0.29
     Petra
    -0.27
    顾
    -0.27
    åĮĹ约
    -0.27
    ãĢĺ
    -0.26
     term
    -0.26
     bomb
    -0.26
    rÄĻ
    -0.25
     caracter
    -0.25
    POSITIVE LOGITS
    ä»İæĿ¥ä¸į
    0.28
     Worth
    0.27
     incarcer
    0.26
    æĭĻ
    0.25
     incremental
    0.25
    crement
    0.25
    该éĻ¢
    0.25
    ilestone
    0.24
    该æ¡Ī
    0.24
    ç§ģ人
    0.23
    Activations Density 2.244%

    No Known Activations