© 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. 4815
    Prev
    Next
    INDEX
    Explanations

    spent time trying

    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
    åŃĺåľ¨ä¸Ģå®ļ
    -0.10
    æľīä¸ĢäºĽ
    -0.10
    urai
    -0.09
     некоÑĤоÑĢÑĭÑħ
    -0.08
     fibr
    -0.08
    è½»æĿ¾
    -0.08
    åĢŁéī´
    -0.08
     thói
    -0.08
    osen
    -0.08
    ç«ĭåį³
    -0.08
    POSITIVE LOGITS
    çīĩéĿ¢
    0.10
    åħīè¾ī
    0.09
    åįķä¸Ģ
    0.09
    æĿ¥äºĨ
    0.09
    åĴĮå®ĮåĸĦ
    0.09
    åIJĦæł·
    0.09
    åįķåįķ
    0.09
    æį¢æĿ¥
    0.08
    éĺ²èĮĥ
    0.08
    å¼Ń
    0.08
    Activations Density 0.213%

    No Known Activations