© 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. 31077
    Prev
    Next
    INDEX
    Explanations

    all rights reserved

    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
    ä¼ļ议精ç¥ŀ
    -0.10
    åºĶåıĬæŶ
    -0.09
    æĪijéĻ¢
    -0.09
    æ¹¾
    -0.09
    éĵ³
    -0.09
    ä¸Ģå¾ĭ
    -0.09
    æµ·å¤ĸå¸Ĥåľº
    -0.09
    顺çĿĢ
    -0.09
    åħ´èµ·
    -0.09
     Bay
    -0.09
    POSITIVE LOGITS
     Ske
    0.09
    ierge
    0.09
    æĮĤéĴ©
    0.08
    wj
    0.08
    геÑĢ
    0.08
     sweat
    0.08
    å®Ļ
    0.08
    kus
    0.08
    ç¿»
    0.07
    æī¿åıĹ
    0.07
    Activations Density 0.056%

    No Known Activations