© 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. 11795
    Prev
    Next
    INDEX
    Explanations

    installation or version information

    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
    ä½ķåĨµ
    -0.10
     ÐĴедÑĮ
    -0.10
    æ¯ķç«Ł
    -0.09
    æĽ´ä½ķåĨµ
    -0.09
    éĴı
    -0.08
    å¹²èĦĨ
    -0.08
    轩
    -0.08
    çĶŃ
    -0.08
    åĬłæ·±
    -0.08
    çĬ¹å¦Ĥ
    -0.08
    POSITIVE LOGITS
    å¥ī
    0.11
    主è¦ģä»İäºĭ
    0.10
    apas
    0.10
    åIJĦæĸ¹éĿ¢
    0.09
    å·²ç»ıå¼Ģå§ĭ
    0.08
    åį¬
    0.08
    åħ¨å¥Ĺ
    0.08
    DataManager
    0.08
    çİ©æ³ķ
    0.08
    çļĦ人æĿ¥è¯´
    0.08
    Activations Density 0.581%

    No Known Activations