© 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. 4343
    Prev
    Next
    INDEX
    Explanations

    problem is that

    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
    nero
    -0.09
    æĢİä¹ĪåĽŀäºĭ
    -0.09
    éĩįè¦ģåİŁåĽł
    -0.09
     Meg
    -0.09
    æ£Ģå¯Łå®ĺ
    -0.09
    ãģĵãģ¨ãģ«
    -0.09
    èĶĹ
    -0.09
    .addClass
    -0.09
    weed
    -0.08
    ankan
    -0.08
    POSITIVE LOGITS
    èĢģ人家
    0.09
    éĿŀ常å¤ļçļĦ
    0.09
    åĪĨæĺİ
    0.09
    éĿŀ常å¤ļ
    0.09
    éĿŀ常æĺİæĺ¾
    0.08
    very
    0.08
    足足
    0.08
    ä¸įçĽ¸ä¿¡
    0.08
    èķĬ
    0.08
    æŀģæĺĵ
    0.08
    Activations Density 0.167%

    No Known Activations