© 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. 52921
    Prev
    Next
    INDEX
    Explanations

    discard or reject

    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
    SURE
    -0.10
    ä¸įåIJĮç¨ĭ度
    -0.09
    odia
    -0.09
     kull
    -0.09
    inium
    -0.09
    æħ¢
    -0.09
     Paging
    -0.08
    黥
    -0.08
    issan
    -0.08
    åĿıäºĭ
    -0.08
    POSITIVE LOGITS
    æİī
    0.11
    UMB
    0.09
    OrUpdate
    0.09
    ä¸ĢåįĬ
    0.08
    æİīäºĨ
    0.08
    egasus
    0.08
     CAB
    0.08
    itech
    0.08
    æĮ¡
    0.08
    hunt
    0.08
    Activations Density 0.027%

    No Known Activations