© 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. 62755
    Prev
    Next
    INDEX
    Explanations

    each new or different

    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
    _ped
    -0.09
    åįĹè·¯
    -0.08
    æ±²
    -0.08
    åIJĦé¡¹å·¥ä½ľ
    -0.08
    ä¸įæĿ¥
    -0.08
    æĿ
    -0.08
    carbon
    -0.08
     пÑĢоб
    -0.08
    é»ijé¾Ļ
    -0.08
    adt
    -0.08
    POSITIVE LOGITS
    ä¸įåIJĮçļĦ
    0.14
    ä¸įä¸Ģæł·çļĦ
    0.11
    æľīä¸įåIJĮçļĦ
    0.11
    raud
    0.09
    ubby
    0.09
    è¦ģä¹Ī
    0.09
    çļĦ主é¢ĺ
    0.09
    éģķãģĨ
    0.09
    ä¸įä¸Ģæł·
    0.08
    ìĶ©
    0.08
    Activations Density 0.072%

    No Known Activations