© 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. 39832
    Prev
    Next
    INDEX
    Explanations

    town hall, open house, information sessions, seminar, fair

    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
    溯
    -0.10
    èµ°å¾Ĺ
    -0.08
    CBC
    -0.08
    åĪ°è´¦
    -0.08
    èĥ½å¤Łåľ¨
    -0.08
    è¾¾æĪIJ
    -0.08
    ä¸Ģå¥Ĺ
    -0.08
    pai
    -0.08
    éĢļè¡Į
    -0.08
     hä
    -0.08
    POSITIVE LOGITS
    çļ±çº¹
    0.11
    ä¸Ģå¹ķ
    0.10
    è°IJ
    0.10
    åı·ç§°
    0.09
    æĿijæ°ij们
    0.09
    ä¸Ģ声
    0.09
    åıijå±ķæł¼å±Ģ
    0.09
     ÑģоÑģед
    0.09
    çļ±
    0.09
    .Dock
    0.08
    Activations Density 0.015%

    No Known Activations