© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10142
    Prev
    Next
    INDEX
    Explanations

    various + types of things

    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
    formance
    -0.09
    º
    -0.09
    æ®į
    -0.09
    æĽ´å¤ļä¿¡æģ¯
    -0.08
    isphere
    -0.08
    o
    -0.08
    æĽ´å¤ļ
    -0.08
    ather
    -0.08
    ex
    -0.08
    isp
    -0.08
    POSITIVE LOGITS
    iance
    0.14
    iating
    0.13
    ly
    0.13
    ially
    0.12
    mente
    0.12
    åIJĦæł·
    0.12
     kinds
    0.12
    -purpose
    0.11
    iable
    0.11
    ä¸įåIJĮçļĦ
    0.11
    Activations Density 0.052%

    No Known Activations