© 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. 38877
    Prev
    Next
    INDEX
    Explanations

    `%clang` or commands after `%`

    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
    pute
    -0.08
    è¾ĵç»Ļ
    -0.08
    ä½İä¿Ŀ
    -0.08
    çł´æįŁ
    -0.08
    å¾Ģä¸ĭ
    -0.08
    æľīæĿ¡ä»¶çļĦ
    -0.08
    çľł
    -0.08
    çĶļèĩ³æĺ¯
    -0.08
    éĢģå¾Ģ
    -0.08
    oc
    -0.08
    POSITIVE LOGITS
    iesel
    0.09
    tures
    0.09
    nbsp
    0.09
    æĿ¥ä¸įåıĬ
    0.09
    lore
    0.09
    åĩºæīĭ
    0.09
    ç¾Ĭæ¯Ľ
    0.08
    ãģĵãģ¨
    0.08
    个å¤ļ
    0.08
    æŶéĹ´åĨħ
    0.08
    Activations Density 0.201%

    No Known Activations