© 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. 33595
    Prev
    Next
    INDEX
    Explanations

    highly

    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
    æĢ»é¢Ŀ
    -0.08
    avax
    -0.08
    åIJģ
    -0.08
    æĽ´æľī
    -0.08
    éĿĻéĿĻ
    -0.08
    好åĿı
    -0.08
    ä¸įè¿ľ
    -0.08
    ä»ĺãģį
    -0.08
    çķ¹
    -0.08
    å¾Ī大
    -0.08
    POSITIVE LOGITS
    é«ĺ度
    0.11
    ä¸ĵä¸ļåĮĸ
    0.10
    责任æĦŁ
    0.09
    çļĦé«ĺ度
    0.09
    é³ĸ
    0.09
    bris
    0.08
    OperationException
    0.08
    æŃī
    0.08
    åĬŁèĥ½æĢ§
    0.08
    Öģ
    0.08
    Activations Density 0.079%

    No Known Activations