© 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. 34125
    Prev
    Next
    INDEX
    Explanations

    US patent numbers

    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
    å¨ĥå¨ĥ
    -0.09
    ArrayOf
    -0.08
    赶
    -0.08
    åĤ¢
    -0.08
    TEX
    -0.08
     kre
    -0.07
    frog
    -0.07
    è·¨è¶Ĭå¼ı
    -0.07
    å¸ĤåľºçļĦ
    -0.07
    æİĪä¿¡
    -0.07
    POSITIVE LOGITS
    è¾Ļ
    0.10
    peare
    0.10
    ç»´å¥ĩ
    0.10
    lient
    0.09
    uckle
    0.09
    yı
    0.09
     dá»ĭ
    0.09
    adol
    0.09
    achat
    0.08
    èijº
    0.08
    Activations Density 0.065%

    No Known Activations