© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50810
    Prev
    Next
    INDEX
    Explanations

    on and off since

    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
    è´±
    -0.10
    nu
    -0.09
    éĿŀ常æĺİæĺ¾
    -0.09
    å±Ĥåĩº
    -0.09
    å¦Ĥå®ŀ
    -0.09
    å¤±æľĽ
    -0.08
    æĪijçĽ¸ä¿¡
    -0.08
    æį£
    -0.08
     Gab
    -0.08
    解åĨ³éĹ®é¢ĺ
    -0.08
    POSITIVE LOGITS
     Twe
    0.08
    æ¡ĵ
    0.08
    (tt
    0.08
    ÙĨÙĪ
    0.08
    åIJĦå¼ı
    0.08
    åī§éĻ¢
    0.08
    çļĦåľ°
    0.08
     íļ
    0.08
    avr
    0.08
    æĦıä¹īä¸ĬçļĦ
    0.08
    Activations Density 0.253%

    No Known Activations