© 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. 22238
    Prev
    Next
    INDEX
    Explanations

    symptoms and conditions

    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
    èµ°è¿ij
    -0.10
    æı£
    -0.10
    çĶŁçĹħ
    -0.09
    æ¦ĤåĨµ
    -0.09
    è¾Ħ
    -0.09
    èIJ¥éĢłèī¯å¥½
    -0.09
    ä¹ĭæīĢ
    -0.08
    åģļå¾Ĺ
    -0.08
    yon
    -0.08
    容纳
    -0.08
    POSITIVE LOGITS
    æ¸ħæī«
    0.10
    é²ľæĺİ
    0.10
    æĮģç»Ń
    0.09
     ÙĦÙħدة
    0.09
    端
    0.08
    gratis
    0.08
     Interracial
    0.08
    _orient
    0.08
    biz
    0.08
     DSM
    0.08
    Activations Density 0.185%

    No Known Activations