© 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. 52935
    Prev
    Next
    INDEX
    Explanations

    authors and artists

    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
    ç¾İçĻ½
    -0.10
    å¡Ķ
    -0.09
    RIX
    -0.09
    ONO
    -0.08
    ä¸įä¿¡
    -0.08
    æĸ°çļĦä¸Ģ
    -0.08
    jspx
    -0.08
    -su
    -0.08
    avigation
    -0.08
    ORS
    -0.08
    POSITIVE LOGITS
    è¯Ģ
    0.10
    è¹Ī
    0.09
    è¦ģæĬĬ
    0.09
    èłķ
    0.09
    #w
    0.09
     chron
    0.08
    å·¥ä¼ļ
    0.08
    溷
    0.08
     Dw
    0.08
    è£ħæī®
    0.08
    Activations Density 0.022%

    No Known Activations