© 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. 10365
    Prev
    Next
    INDEX
    Explanations

    how to search online

    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
    ä¸įå®ļ
    -0.10
    æĤłéĹ²
    -0.09
    .Serializer
    -0.09
    èĿ
    -0.09
    ä¸Ģå°ģ
    -0.09
    éĢļéģĵ
    -0.09
    毫ä¸įçĬ¹è±«
    -0.09
    磼
    -0.09
    stown
    -0.09
    èij±
    -0.08
    POSITIVE LOGITS
    åľ¨çº¿
    0.10
    糧
    0.09
     rav
    0.08
    åľ¨çº¿åĴ¨è¯¢
    0.08
    æĦŁåħ´è¶£çļĦ
    0.08
    ä¹Łå¥½
    0.08
     online
    0.08
    人士
    0.08
    éĿłè°±
    0.08
    åı£ç¢ij
    0.08
    Activations Density 0.257%

    No Known Activations