© 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. 30312
    Prev
    Next
    INDEX
    Explanations

    trademarks, trade secrets, service marks

    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
    ç³Ĭæ¶Ĥ
    -0.11
    æľīå¤ļ
    -0.09
    çīĪæĿĥ
    -0.09
    æ²£
    -0.09
    çļĦæĸ¹åIJij
    -0.09
    åĴĮå®ĮåĸĦ
    -0.08
    çݯèĬĤ
    -0.08
    éĢŀ
    -0.08
    æĺ¯æ²¡æľī
    -0.08
     fix
    -0.08
    POSITIVE LOGITS
    è®Ń
    0.10
    Homepage
    0.09
    è¨ĵ
    0.09
    URN
    0.09
    +xml
    0.09
    stitution
    0.09
    æĥ¯ä¾ĭ
    0.09
    LBL
    0.09
    æĦ
    0.08
    çªľ
    0.08
    Activations Density 0.034%

    No Known Activations