© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 3952
    Prev
    Next
    INDEX
    Explanations

    made a request or inquiry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Öģ
    -0.09
    åĽłä¸ºä»ĸ们
    -0.09
    rush
    -0.08
    åı¯ä»¥è¯´
    -0.08
     trg
    -0.08
    è¿Ł
    -0.08
    çľĭèijĹ
    -0.08
    èľļ
    -0.08
    é©·
    -0.08
    utton
    -0.08
    POSITIVE LOGITS
    éĻIJæŶ
    0.11
    éĻIJ度
    0.10
    çļĦå°±æĺ¯
    0.10
     Pieces
    0.10
     Rac
    0.09
    éĻIJæľŁ
    0.08
    æįİ
    0.08
    åĭĻ
    0.08
    maal
    0.08
    èĥģ
    0.08
    Activations Density 0.016%

    No Known Activations