© 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. 26979
    Prev
    Next
    INDEX
    Explanations

    or or

    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
    æĽĻåħī
    -0.11
    没éĶĻ
    -0.10
    æ¿ij
    -0.10
     Flam
    -0.09
     flam
    -0.09
    èĢģçīĮ
    -0.09
    åİļåİļçļĦ
    -0.09
    ä¸įåĬ¨
    -0.09
    è¿Ļ两年
    -0.09
    çªį
    -0.09
    POSITIVE LOGITS
    å¢ĥå¤ĸ
    0.08
    iphy
    0.08
    綦
    0.07
    PMC
    0.07
    EXTERN
    0.07
    å¼Ń
    0.07
     cheated
    0.07
     Kah
    0.07
    åĸĿèĮ¶
    0.07
    utr
    0.07
    Activations Density 0.143%

    No Known Activations