© 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. 37949
    Prev
    Next
    INDEX
    Explanations

    cinemagraph loop, time lapse video

    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
    éĢĤ
    -0.09
    æ·±åĮĸæĶ¹éĿ©
    -0.09
     simul
    -0.09
    Army
    -0.09
    TickCount
    -0.08
    ruit
    -0.08
    äºĭåħĪ
    -0.08
     dood
    -0.08
     CMP
    -0.08
    ଡ
    -0.08
    POSITIVE LOGITS
    çħ§æĸĻ
    0.10
    士
    0.10
    æĸĻ
    0.09
    æ¯ıæĹ¥
    0.09
     brag
    0.09
    æ¯ı天
    0.09
    LT
    0.09
    æĭ¼
    0.09
    ç¾İ丽
    0.09
    еннÑĥÑİ
    0.08
    Activations Density 0.101%

    No Known Activations