© 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. 36022
    Prev
    Next
    INDEX
    Explanations

    Great Lakes, New York, Jesuits, Algonquin Books

    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
    opers
    -0.10
    oller
    -0.09
    æĻĭæ±Ł
    -0.09
    稼
    -0.08
     Mavericks
    -0.08
    éĻĮ
    -0.08
    åĽĽæĸ¹
    -0.08
    é£İæ°Ķ
    -0.08
    è·ij
    -0.08
    urch
    -0.08
    POSITIVE LOGITS
    ä¼IJ
    0.12
    .ca
    0.11
    æľ¨æĿIJ
    0.11
    åĬłæĭ¿å¤§
    0.10
    æįķé±¼
    0.10
     Toronto
    0.10
    æŀ«
    0.10
    æ¹ĸæ³Ĭ
    0.10
    æ¹ĸ
    0.10
    Toronto
    0.10
    Activations Density 0.198%

    No Known Activations