© 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. 53532
    Prev
    Next
    INDEX
    Explanations

    worn, used, wear

    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
    ients
    -0.09
    ળ
    -0.09
    夺åıĸ
    -0.09
    解
    -0.09
    æĦļ
    -0.08
    çĪ¬
    -0.08
     зай
    -0.08
    ivery
    -0.08
    æݧåĪ¶
    -0.08
    MAND
    -0.08
    POSITIVE LOGITS
    磨æįŁ
    0.17
    æŃ£å¸¸ä½¿çĶ¨
    0.17
     wear
    0.15
    æĬķåħ¥ä½¿çĶ¨
    0.12
     usage
    0.12
     worn
    0.12
     Wear
    0.11
    wear
    0.11
    èĢIJ磨
    0.11
    usage
    0.11
    Activations Density 0.095%

    No Known Activations