© 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. 48290
    Prev
    Next
    INDEX
    Explanations

    simple things, ideas, and pleasures

    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
    antz
    -0.10
    .ov
    -0.09
    _runtime
    -0.08
    æĸ½å±ķ
    -0.08
    ãģ£ãģ
    -0.08
    åķĨæĬ¥
    -0.08
    èĪª
    -0.08
    éĿ¢çĻ½
    -0.08
    oki
    -0.08
    éľĩåĬ¨
    -0.08
    POSITIVE LOGITS
    ä¸ĸéĹ´
    0.11
    èįī
    0.11
    ç®Ģåįķ
    0.11
    奢ä¾Īåĵģ
    0.10
     things
    0.10
    æ¯Ķè¾ĥç®Ģåįķ
    0.10
    æĸĩåĮĸåĴĮ
    0.10
     pleasures
    0.10
    ç°¡åĸ®
    0.10
    äºĭçī©
    0.10
    Activations Density 0.043%

    No Known Activations