© 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. 29879
    Prev
    Next
    INDEX
    Explanations

    popular languages

    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
    çļĦç§ĺå¯Ĩ
    -0.11
    ä»»æľŁ
    -0.09
    åľ¨å®¶éĩĮ
    -0.09
    ä¸ĢåĪĢ
    -0.09
    ç¢
    -0.09
    _trait
    -0.08
    åĪ»
    -0.08
    æ¯Ķä¾ĭ
    -0.08
    ä»ħæľī
    -0.08
    è¿ĺä¸įæĺ¯
    -0.08
    POSITIVE LOGITS
    å¹¿æ³ĽçļĦ
    0.11
    å¹¿æ³Ľ
    0.10
     popular
    0.09
     famously
    0.09
    家åĸ»æĪ·æĻĵ
    0.09
    çĥŃéŨ
    0.09
    IDEO
    0.09
    æĺ¯ä¸Ģç§į
    0.08
    çĽ¸ä¿¡å¤§å®¶
    0.08
    popular
    0.08
    Activations Density 0.357%

    No Known Activations