© 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. 49327
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
    ×ķ
    -0.10
    [
    -0.09
    ors
    -0.09
    ive
    -0.09
    ãģĤãĤĭ
    -0.09
    -looking
    -0.08
    Ùĩا
    -0.08
    æĺİå¹´
    -0.08
    ful
    -0.07
     именно
    -0.07
    POSITIVE LOGITS
    /from
    0.10
    åīįæīĢ
    0.10
    èĢģ人家
    0.09
    个å¤ļ
    0.09
    ç´ļ
    0.09
    ALLY
    0.09
    semb
    0.09
    æĪĸèĢħåħ¶ä»ĸ
    0.09
    TRL
    0.08
    æ´º
    0.08
    Activations Density 2.156%

    No Known Activations