© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20350
    Prev
    Next
    INDEX
    Explanations

    questions asking for clarification

    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
    åĸĬ
    -0.08
    ãģ£ãģ¨
    -0.08
    rs
    -0.08
    åŃĺåľ¨çĿĢ
    -0.08
    åŀĤ
    -0.08
    ä¸įèĥ½åĨį
    -0.08
    äºĭä¸ļ
    -0.08
    _MR
    -0.07
    éĿŀ常éĢĤåIJĪ
    -0.07
    对æĪijæĿ¥è¯´
    -0.07
    POSITIVE LOGITS
    è¿ĻæĶ¯
    0.11
    luck
    0.11
     denn
    0.10
     Fort
    0.10
    æ¿ŀ
    0.10
    è¿ĺè®°å¾Ĺ
    0.09
    åı¯è§Ĥ
    0.09
    èıģ
    0.09
    atics
    0.09
    ä¸Ĭ课
    0.09
    Activations Density 0.067%

    No Known Activations