© 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. 30303
    Prev
    Next
    INDEX
    Explanations

    Now

    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
    é¡ĺ
    -0.26
    æµĴ
    -0.25
     rep
    -0.25
     reign
    -0.25
    ClassNotFoundException
    -0.24
     favour
    -0.24
    衽
    -0.24
    å²±
    -0.24
     deserted
    -0.24
    箾
    -0.24
    POSITIVE LOGITS
    éĶģå®ļ
    0.26
    *****↵↵
    0.26
    edy
    0.26
     COMMIT
    0.25
    #↵↵
    0.25
    ög
    0.25
    鸽
    0.24
    headed
    0.24
    é¢ijéģĵ
    0.24
    vous
    0.24
    Activations Density 0.681%

    No Known Activations