© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7162
    Prev
    Next
    INDEX
    Explanations

    there are many

    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
    .po
    -0.09
    çŃĶå¤į
    -0.09
    æľ¬äºº
    -0.09
    åħļä¸Ń央
    -0.08
    moz
    -0.08
    éģµå¾ª
    -0.08
    æĤ¨çļĦåŃ©åŃIJ
    -0.08
    esc
    -0.08
    ç±´
    -0.08
    rases
    -0.08
    POSITIVE LOGITS
    asia
    0.10
    htag
    0.09
    å¼Ĥåij³
    0.09
    顾èĻij
    0.09
    äºĨä¸įå°ij
    0.09
    ä¸ĵéĹ¨ä¸º
    0.08
    أخبار
    0.08
    çŃ¼
    0.08
    rier
    0.08
    çĻĸ
    0.08
    Activations Density 0.046%

    No Known Activations