© 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. 21690
    Prev
    Next
    INDEX
    Explanations

    Copyright Inc

    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
    æѦæŀĹ
    -0.09
     Ott
    -0.09
     пÑĢоиÑģ
    -0.09
    ä¸ŃåĽ½æĶ¿åºľ
    -0.09
    设计åĻ¨
    -0.08
    èĨĤ
    -0.08
    æĻ¯å¾·
    -0.08
    Indented
    -0.08
     Outlet
    -0.08
     tap
    -0.08
    POSITIVE LOGITS
    伶
    0.10
    绸
    0.09
    失èIJ½
    0.09
    åĨ»
    0.09
    åŃ£
    0.09
    ä¸īåĨľ
    0.09
    çľī
    0.08
    antu
    0.08
    åºľ
    0.08
    è°ĵ
    0.08
    Activations Density 0.073%

    No Known Activations