© 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. 2313
    Prev
    Next
    INDEX
    Explanations

    rights and entitlements

    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
    ä¸įå·²
    -0.10
    åĽ´çĿĢ
    -0.09
    èŀį
    -0.09
    è¦ģçľĭ
    -0.09
    иÑĪÑĮ
    -0.09
    æĺ¯æĢİæł·
    -0.09
    åĽŀéģ¿
    -0.08
    çĮ¥
    -0.08
    é¢Ĩä¼ļ
    -0.08
    &&!
    -0.08
    POSITIVE LOGITS
    æľīæĿĥ
    0.19
    çļĦæĿĥåĪ©
    0.16
    æĿĥåĪ©
    0.15
     rights
    0.14
     entitled
    0.13
     пÑĢаво
    0.12
    享æľī
    0.12
     ê¶Į리
    0.12
    æ¬ĬåĪ©
    0.12
     пÑĢава
    0.12
    Activations Density 0.070%

    No Known Activations