© 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. 52459
    Prev
    Next
    INDEX
    Explanations

    publications and articles

    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
    绣
    -0.09
    ä¸ĩ个
    -0.09
    æ½ĩæ´Ĵ
    -0.09
    å®ĺ
    -0.08
     Schmidt
    -0.08
    èĢĮæĿ¥
    -0.08
    rac
    -0.08
    oga
    -0.08
    .conf
    -0.08
    ABEL
    -0.08
    POSITIVE LOGITS
    åıij表
    0.21
    论æĸĩ
    0.17
    çĻ¼è¡¨
    0.17
    åıij表äºĨ
    0.17
    æĪIJæŀľ
    0.16
    åħ¬å¼Ģåıij
    0.16
    åŃ¦æľ¯
    0.15
    èijĹä½ľ
    0.15
     publications
    0.15
    åĪĬçī©
    0.15
    Activations Density 0.100%

    No Known Activations