© 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. 6349
    Prev
    Next
    INDEX
    Explanations

    guard

    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
     Blond
    -0.09
    odore
    -0.09
    rl
    -0.08
    ä¸įè¿ĩæĺ¯
    -0.08
    odor
    -0.08
    ł
    -0.08
    ç§Ĩ
    -0.08
    ¾
    -0.08
    inki
    -0.08
     Conn
    -0.08
    POSITIVE LOGITS
    iola
    0.09
    ÙģÙĤ
    0.09
    _BOTH
    0.09
    ساÙħ
    0.09
    uet
    0.09
    æĺ¯éĿŀ
    0.09
    蹶
    0.09
    åĸĿèĮ¶
    0.09
    æĭİ
    0.09
    æ¼ı
    0.08
    Activations Density 0.002%

    No Known Activations