© 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. 55239
    Prev
    Next
    INDEX
    Explanations

    pectin

    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
    绿åĮĸ
    -0.09
    èįĨå·ŀ
    -0.09
    aign
    -0.09
    åIJĮæľŁ
    -0.08
    æĺ¥åŃ£
    -0.08
    è§Ĭ
    -0.08
    ŀæĢ§
    -0.08
     ghé
    -0.08
    åѱ
    -0.08
    ä¸Ńå¤ĸ
    -0.08
    POSITIVE LOGITS
    inery
    0.09
    馥
    0.09
     Vibr
    0.08
     Vic
    0.08
    æĸijæĸĵ
    0.08
    èĩĬ
    0.08
    ANNER
    0.08
    æµĵ
    0.08
    oops
    0.08
    èįĶæŀĿ
    0.08
    Activations Density 0.011%

    No Known Activations