© 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. 38873
    Prev
    Next
    INDEX
    Explanations

    to say the least

    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¸ĵéŨ
    -0.08
    ç©Ĺ
    -0.08
    venir
    -0.08
    allen
    -0.08
    avery
    -0.08
    éĩįè¦ģ
    -0.08
    ry
    -0.08
    /Set
    -0.08
    ittal
    -0.08
    empo
    -0.08
    POSITIVE LOGITS
    è¿Ļ个è¯į
    0.11
    ä¸į论
    0.11
    è¿Ļæł·è¯´
    0.10
    ä»Ģä¹Īåı«
    0.10
    æ´±
    0.09
    欢è¿İæĤ¨
    0.09
    è¿Ļåı¥è¯Ŀ
    0.09
    äºĮåŃĹ
    0.09
    éĤ£ä½į
    0.09
    æĸĭ
    0.09
    Activations Density 0.052%

    No Known Activations