© 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. 31114
    Prev
    Next
    INDEX
    Explanations

    ç¼ĸç»ĩ aga ç§ij缮

    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
    cer
    -0.09
     Trit
    -0.09
    ols
    -0.08
    å¼ĺæī¬
    -0.08
    _impl
    -0.08
    ICI
    -0.08
    æ¼ī
    -0.08
    çIJ
    -0.08
     Seam
    -0.08
     lids
    -0.07
    POSITIVE LOGITS
    ç¼ł
    0.11
    æĭ´
    0.10
    绳
    0.10
    æĿ¾å¼Ľ
    0.10
    ç»ķ
    0.09
    ç¹ŀ
    0.09
    产ä¸ļåĽŃåĮº
    0.09
    ç¼ĸç»ĩ
    0.09
    aga
    0.09
    ç§ij缮
    0.09
    Activations Density 0.198%

    No Known Activations