© 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. 29831
    Prev
    Next
    INDEX
    Explanations

    enter or go into

    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·¯æ¼Ķ
    -0.10
    ç¿Ĭ
    -0.09
     оÑĤд
    -0.09
    -toast
    -0.09
    _DISP
    -0.09
    æĦıä¹īä¸ĬçļĦ
    -0.09
     khả
    -0.09
    æīĭèĦļ
    -0.09
    æĦıä¹īä¸Ĭ
    -0.09
    SupportedContent
    -0.09
    POSITIVE LOGITS
    è¿ĽæĿ¥
    0.31
    è¿Ľåİ»
    0.25
    åħ¥
    0.19
    è¿Ľåħ¥
    0.17
    è¿ĽäºĨ
    0.16
    è¿ĽéŨ
    0.16
    è¿Ľ
    0.16
     into
    0.15
    éĢ²åħ¥
    0.15
    æīĵè¿Ľ
    0.14
    Activations Density 0.155%

    No Known Activations