© 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. 55018
    Prev
    Next
    INDEX
    Explanations

    Yolo technologies

    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¸ĢèĪ¬æĺ¯
    -0.10
    æı£
    -0.09
    ç½į
    -0.09
    å°ı鸣
    -0.09
    æ¼ıæ°´
    -0.09
    èĥĮä¸Ĭ
    -0.09
    ä»İæĿ¥ä¸į
    -0.08
    çĿ«
    -0.08
    éĹ®ä»ĸ
    -0.08
    æķıæĦŁ
    -0.08
    POSITIVE LOGITS
    prs
    0.10
    ismo
    0.08
    loh
    0.08
    ists
    0.08
    åĨ³èµĽ
    0.08
    ombine
    0.08
     عÙħر
    0.08
    èĤ¡
    0.08
     mange
    0.08
    æ±ĩ
    0.08
    Activations Density 0.072%

    No Known Activations