© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9410
    Prev
    Next
    INDEX
    Explanations

    aman Raman crystal Award Buchanan Dow .svg Pass support

    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
    endo
    -0.09
    æļ´
    -0.09
    eyer
    -0.09
    oard
    -0.09
    ynchronously
    -0.08
    è¿IJ
    -0.08
    ator
    -0.08
    nature
    -0.08
    velt
    -0.08
    èĪ«
    -0.08
    POSITIVE LOGITS
    åĽ½éĻħå¸Ĥåľº
    0.09
    alty
    0.09
    imum
    0.08
    åŀĤ
    0.08
     gyr
    0.08
    åĨĽåĽ¢
    0.08
    海峡
    0.08
    å¹³æĿ¿
    0.08
    ç»ij
    0.08
    åħ¨éĿ¢èIJ½å®ŀ
    0.08
    Activations Density 0.003%

    No Known Activations