© 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. 23431
    Prev
    Next
    INDEX
    Explanations

    past years

    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
    åIJİæĿ¥
    -0.13
    å½ĵæŶ
    -0.13
    å½ĵæŶçļĦ
    -0.12
    å½ĵåĪĿ
    -0.11
    åIJİéĿ¢çļĦ
    -0.10
    å¾Įä¾Ĩ
    -0.10
    å½ĵå¹´
    -0.10
    later
    -0.10
    ä¸Ģæĸ¹
    -0.10
    ãģĿãģ®å¾Į
    -0.10
    POSITIVE LOGITS
    éĥ½å°Ĩ
    0.09
    ä¸ĢçĽ´åľ¨
    0.09
    éĥ½åľ¨
    0.09
    à¸Ĥà¸Ńà¸ĩà¸ģาร
    0.09
    åĪĨåĪ«æĺ¯
    0.09
    éĥ½æĺ¯
    0.09
    abouts
    0.08
    éĥ½éĿŀ常
    0.08
    åĴĮåľ°åĮº
    0.08
    éĥ½å·²ç»ı
    0.08
    Activations Density 0.047%

    No Known Activations