© 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. 34081
    Prev
    Next
    INDEX
    Explanations

    shoe repair

    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
    è½°
    -0.11
    æĸĩåŃĹ
    -0.08
    çĽij
    -0.08
    ä½ĺ
    -0.08
    aus
    -0.08
    /tiny
    -0.08
    çĶŁçī©åѦ
    -0.08
    æŁ½
    -0.08
    æĭŃ
    -0.08
    kening
    -0.08
    POSITIVE LOGITS
    ç»´ä¿®
    0.19
    ä¿®çIJĨ
    0.19
     repair
    0.17
    ä¿®å¤į
    0.17
    ä¿®
    0.15
    repair
    0.15
     Repair
    0.14
    修补
    0.14
     repairs
    0.13
    Repair
    0.13
    Activations Density 0.094%

    No Known Activations