© 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. 4661
    Prev
    Next
    INDEX
    Explanations

    convene, inform, include, break, investigate

    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
    åįĥéĩĮ
    -0.09
    ç´¢èµĶ
    -0.09
    æĩĴå¾Ĺ
    -0.08
     Filip
    -0.08
    æ³ķè§Ħ
    -0.08
    è¾ķ
    -0.08
    inish
    -0.08
    éĿ¢å¯¹éĿ¢
    -0.08
    esp
    -0.07
     my
    -0.07
    POSITIVE LOGITS
    æ¯ıéĢ¢
    0.10
    强çĥĪ
    0.10
    ç°§
    0.09
    çĶ·ä¸»è§Ĵ
    0.09
    _CID
    0.09
    ä¸ĸçķĮä¸Ģæµģ
    0.09
     erle
    0.08
    åı¯è¡Į
    0.08
    æĽ´å¤ļ精彩
    0.08
    ç½į
    0.08
    Activations Density 0.059%

    No Known Activations