© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 16915
    Prev
    Next
    INDEX
    Explanations

    syllable formation

    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
    าย
    -0.09
    åĩĢ
    -0.09
    isseur
    -0.08
    ersion
    -0.08
    aint
    -0.08
    alls
    -0.08
    åħ¨æł¡
    -0.08
    ï¸ı
    -0.08
    CharArray
    -0.08
    /place
    -0.08
    POSITIVE LOGITS
    æİīäºĨ
    0.10
    éĽĢ
    0.10
    åĥŃ
    0.10
     foregoing
    0.10
    åĴĮæĬĢæľ¯
    0.09
    éĻ¡
    0.09
    干货
    0.09
    æĦį
    0.09
    arity
    0.09
    人家
    0.09
    Activations Density 0.003%

    No Known Activations