© 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. 23890
    Prev
    Next
    INDEX
    Explanations

    quantifying impacts or occurrences

    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
    ä¸ĢåĪĨ
    -0.09
    enger
    -0.09
    å¥¥åľ°åĪ©
    -0.09
    ç§ĺ书éķ¿
    -0.08
    illion
    -0.08
    mill
    -0.08
    èĬ±éĴ±
    -0.08
    ادر
    -0.08
    æŀĦæĪIJäºĨ
    -0.08
    ç¬ijè¯Ŀ
    -0.08
    POSITIVE LOGITS
     дополниÑĤелÑĮно
    0.09
    зал
    0.09
    æŃ¤äºº
    0.09
    ä¿Ń
    0.08
    ä¸ºæľŁ
    0.08
    å¹¢
    0.08
    åħī线
    0.08
    éĺģ
    0.08
     ÐľÐµ
    0.08
    ä¸Ģéĺµ
    0.08
    Activations Density 0.034%

    No Known Activations