© 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. 34299
    Prev
    Next
    INDEX
    Explanations

    HIV-1

    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
     Burgess
    -0.10
    æ·±åİļçļĦ
    -0.09
    è¿İæİ¥
    -0.09
    书éĻ¢
    -0.09
    éĻįä»·
    -0.09
     Tablets
    -0.09
    .Criteria
    -0.08
    å¾Ĺ罪
    -0.08
    ä½ĵ系建设
    -0.08
    roy
    -0.08
    POSITIVE LOGITS
    媵
    0.10
    åIJ¦
    0.09
    åĵĢ
    0.09
    ä¸įæĪIJ
    0.09
    ä¹į
    0.09
    使æĪij
    0.08
    饰
    0.08
    .fig
    0.08
    粤港澳
    0.08
    鸳
    0.08
    Activations Density 0.160%

    No Known Activations