© 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. 3699
    Prev
    Next
    INDEX
    Explanations

    describing items

    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
    绫
    -0.08
    sheet
    -0.08
    uje
    -0.08
    imum
    -0.08
    ç¾Ĭ
    -0.08
    erv
    -0.08
    åĨħè¡£
    -0.08
    -exc
    -0.07
    itaire
    -0.07
    burg
    -0.07
    POSITIVE LOGITS
    åĩºèĩª
    0.10
    æĿ¥èĩª
    0.10
    å·§
    0.10
    пÑĢод
    0.09
     Downing
    0.09
     sale
    0.09
    æĿ¥èĩªäºİ
    0.09
    æĪIJåĵģ
    0.09
    ä¸Ģä½ĵ
    0.09
    å°ıå·§
    0.09
    Activations Density 0.062%

    No Known Activations