© 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. 6672
    Prev
    Next
    INDEX
    Explanations

    storage and preservation

    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
    è¿·
    -0.10
    äºĨåĩºæĿ¥
    -0.09
    ä¾
    -0.08
    ê¼´
    -0.08
    ç»ĻäºĨ
    -0.08
    头èĦij
    -0.08
     Tyler
    -0.08
    äºĨä¸Ģåı¥
    -0.08
    -runtime
    -0.08
    æĪ¿åŃIJ
    -0.08
    POSITIVE LOGITS
    ä¸įå®Į
    0.10
    chos
    0.10
    ìķ¼
    0.09
    _pri
    0.09
    åºŁ
    0.09
    ennon
    0.09
    ket
    0.09
    éļĶ
    0.09
    å¨ĺ
    0.08
    éķ¿éĢĶ
    0.08
    Activations Density 0.038%

    No Known Activations