© 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. 32-TRANSCODER-HP
    7. 44102
    Prev
    Next
    INDEX
    Explanations

    hand

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    {/
    -0.28
    éļıçĿĢæŶéĹ´
    -0.27
    ¤
    -0.27
    ¢åįķ
    -0.26
    ÑĢам
    -0.26
    èĭĶ
    -0.25
    éĿĴ
    -0.24
    âķ¯
    -0.24
    айд
    -0.24
    ')}}
    -0.24
    POSITIVE LOGITS
    still
    0.47
     still
    0.44
     STILL
    0.38
    Still
    0.38
     Still
    0.37
    ä»įå°Ĩ
    0.35
    ä»įçĦ¶
    0.31
    ä»įæľª
    0.29
     ancora
    0.28
    ä»įæĺ¯
    0.28
    Activations Density 0.003%

    No Known Activations