© 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. 48391
    Prev
    Next
    INDEX
    Explanations

    South Africa

    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
    æĺĿ
    -0.10
    æĭ¾
    -0.09
    _VOID
    -0.09
    ç¥ľ
    -0.09
     Sabb
    -0.09
    æľ´
    -0.08
    éĶº
    -0.08
    è¶ĭ
    -0.08
    èĢĮæĿ¥
    -0.08
    ä¼ŀ
    -0.08
    POSITIVE LOGITS
    å®ĺ
    0.09
    æľĢ好
    0.09
    åIJ¾
    0.09
     Fur
    0.08
    izard
    0.08
    els
    0.08
    Freq
    0.08
    æľĢ大ç¨ĭ度
    0.08
    æĸ½è¡Į
    0.08
    åħ¸åŀĭ
    0.08
    Activations Density 0.038%

    No Known Activations