© 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. 21869
    Prev
    Next
    INDEX
    Explanations

    people's names

    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
    åľ¨è¿Ļ
    -0.10
    çŁŃçŁŃ
    -0.09
    纥
    -0.09
    åį³å°ĨåĪ°æĿ¥
    -0.09
    ä¸įä¹ħ
    -0.09
    ISO
    -0.08
    å§Ķç»Ħç»ĩ
    -0.08
    ç»IJ
    -0.08
    åĴĮ个人
    -0.08
    æį®æѤ
    -0.08
    POSITIVE LOGITS
    alse
    0.08
    ç¼Ķ
    0.08
    è°±åĨĻ
    0.08
    æħķ
    0.08
    è¡Ĺ头
    0.08
    å±
    0.08
    PropertyDescriptor
    0.08
    à¹Ĥà¸Ķ
    0.08
    EIF
    0.08
    å¥
    0.08
    Activations Density 0.079%

    No Known Activations