© 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. 38854
    Prev
    Next
    INDEX
    Explanations

    told you 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
    åħīçݯ
    -0.09
    æģ©
    -0.09
    åīį身
    -0.08
    ลำ
    -0.08
    aÄĩ
    -0.08
    è¯ŀ
    -0.08
    第ä¸Ģå±Ĭ
    -0.08
     Reads
    -0.08
    abet
    -0.08
    æĺ¯ä¸Ģ项
    -0.07
    POSITIVE LOGITS
    说è¿ĩ
    0.14
    ä¸Ģ缴éĥ½
    0.11
    æĹłæķ°æ¬¡
    0.11
    èѦåijĬ
    0.11
    åij¼åIJģ
    0.10
    ä¸»å¼ł
    0.10
    æıIJéĨĴ
    0.10
     suá»ijt
    0.10
    è°Ĩ
    0.10
     warnings
    0.09
    Activations Density 0.038%

    No Known Activations