© 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. 24-TRANSCODER-HP
    7. 149236
    Prev
    Next
    INDEX
    Explanations

    Code/programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    odore
    -0.27
    ctrl
    -0.27
     ctrl
    -0.26
    ä¸ĭåįĬ
    -0.26
     CK
    -0.26
    weep
    -0.25
     rand
    -0.25
     control
    -0.25
    voor
    -0.25
    iate
    -0.24
    POSITIVE LOGITS
    æijĦ
    0.32
    çĹķ迹
    0.30
    èĬĿ
    0.28
    é¢Ĥ
    0.28
     trot
    0.24
    ä½Ĩæĺ¯ä»ĸ
    0.24
     maj
    0.24
    _TODO
    0.24
    Stride
    0.23
    足迹
    0.23
    Activations Density 0.105%

    No Known Activations