© 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. 62690
    Prev
    Next
    INDEX
    Explanations

    first mechanism, factor, one, data, series

    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
    ç«£
    -0.10
    åIJĦèĩªçļĦ
    -0.09
    ãģĤãĤĬãģ¾ãģĽãĤĵ
    -0.09
    åij¨å¹´
    -0.09
    æľ¬èº«çļĦ
    -0.09
    åĿĩæľī
    -0.08
    èµĸ以
    -0.08
    们çļĦ
    -0.08
    éĢĥéģ¿
    -0.08
    å°±ç®Ĺ
    -0.08
    POSITIVE LOGITS
    æĭħå¿ĥ
    0.11
    æĭħ忧
    0.10
    è¿ĻçĤ¹
    0.10
    ç«ł
    0.10
    è¿Ļä¸ĢçĤ¹
    0.09
    iciel
    0.09
    ç¾ģ
    0.09
    éĥ¢
    0.09
     concern
    0.09
    æĸ¹éĿ¢
    0.09
    Activations Density 0.060%

    No Known Activations