© 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. 57839
    Prev
    Next
    INDEX
    Explanations

    CD singles and versions

    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
    åIJ¼
    -0.11
    ç¬ı
    -0.11
    æ°IJ
    -0.10
    å¾Ĺä½ı
    -0.09
     trÃŃ
    -0.09
    flows
    -0.09
    opi
    -0.08
    isse
    -0.08
     Yan
    -0.08
    èĻ¾
    -0.08
    POSITIVE LOGITS
     overhead
    0.10
    åŁĭ
    0.09
    -site
    0.09
    å±¥
    0.09
     Levin
    0.09
    æĢ¥åī§
    0.09
    第ä¸Ģæī¹
    0.08
     Lear
    0.08
     Ske
    0.08
    .Site
    0.08
    Activations Density 0.168%

    No Known Activations