© 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. 57962
    Prev
    Next
    INDEX
    Explanations

    things followed by adverbial phrases

    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
    çĨ¨
    -0.09
    ãģ»ãģĨãģĮ
    -0.09
    çļĦæĪIJ绩
    -0.09
    è°ĥåĬ¨
    -0.09
    åIJĦæł·
    -0.09
    çĹħæ¯ĴæĦŁæŁĵ
    -0.09
    人éĢī
    -0.08
    æĹ¥èµ·
    -0.08
    客è¿IJ
    -0.08
    isphere
    -0.08
    POSITIVE LOGITS
     Edwin
    0.09
    uture
    0.08
    åıĺå¾ĹæĽ´åĬł
    0.08
     Zuk
    0.08
    astes
    0.08
    è¿ĩå¾Ĺ
    0.08
    åı¬åĽŀ
    0.08
    ç²¾çĽĬæ±Ĥç²¾
    0.08
    asString
    0.08
    羣缸
    0.08
    Activations Density 0.018%

    No Known Activations