© 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. 11386
    Prev
    Next
    INDEX
    Explanations

    myself, herself, entirely, completely

    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
    ettel
    -0.11
    ä¸įå¦Ĥ
    -0.10
    resenter
    -0.09
    endors
    -0.09
     SEAL
    -0.09
     Nr
    -0.09
     fant
    -0.08
    è
    -0.08
    æĸĹ
    -0.08
    ä¸Ģ大æī¹
    -0.08
    POSITIVE LOGITS
    亲èĩª
    0.11
    亲æīĭ
    0.11
    åħ¨éĥ¨
    0.11
     entirely
    0.10
    éĿł
    0.09
    ç»Ŀ大éĥ¨åĪĨ
    0.09
    积åĪĨ
    0.09
    大éĥ¨åĪĨ
    0.08
    åĴ¨è¯¢æľįåĬ¡
    0.08
    ç»ĨåĪĻ
    0.08
    Activations Density 0.054%

    No Known Activations