© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52359
    Prev
    Next
    INDEX
    Explanations

    sample size and conclusions

    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
    bsolute
    -0.09
    è¶ĬæĿ¥
    -0.09
    æĦıèŃĺ
    -0.09
    åĵŃ
    -0.09
     desn
    -0.08
     Pepper
    -0.08
    çļĦåĬ¨åĬĽ
    -0.08
    icorn
    -0.08
    èī¾
    -0.08
     thừa
    -0.08
    POSITIVE LOGITS
    æł·æľ¬
    0.13
    ä¸į足以
    0.12
    代表æĢ§
    0.11
    并ä¸į代表
    0.11
    太å°ij
    0.10
    æ¯ķç«Łæĺ¯
    0.10
    ä¸į代表
    0.09
    åĮĨåĮĨ
    0.09
    åĨµä¸Ķ
    0.09
    ä¸įç®Ĺ
    0.09
    Activations Density 0.058%

    No Known Activations