© 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. 39496
    Prev
    Next
    INDEX
    Explanations

    at age of

    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
    åĪ©çĶ¨
    -0.10
    ÑĪед
    -0.09
    amp
    -0.09
     Amp
    -0.08
    åŃ½
    -0.08
    ç´§æİ¥çĿĢ
    -0.08
    antha
    -0.08
     ÑĢаÑģположен
    -0.08
    éĢĶ
    -0.08
    积èĵĦ
    -0.08
    POSITIVE LOGITS
    ermal
    0.09
    ä¸ĥåħ«
    0.09
    леÑĩ
    0.09
    夺åĨł
    0.09
    çĻ½æĸij
    0.09
    ä¸Ģ大
    0.08
    æĭ¿äºĨ
    0.08
    ALSE
    0.08
    تا
    0.08
    'gc
    0.08
    Activations Density 0.085%

    No Known Activations