© 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. 62247
    Prev
    Next
    INDEX
    Explanations

    emperor, century, spirit, age, android

    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
    éĺħ读åħ¨æĸĩ
    -0.10
    æľªç»ıæİĪæĿĥ
    -0.09
    ect
    -0.09
    åľ¨æ¸¸æĪıä¸Ń
    -0.09
    ä»ħ代表
    -0.09
    ç¾°
    -0.09
    æĦıæĢĿ
    -0.08
    éħļ
    -0.08
    åħħåĪĨä½ĵçİ°
    -0.08
     mount
    -0.08
    POSITIVE LOGITS
    å¸ĥ
    0.09
    oric
    0.09
     Myers
    0.09
    BOSE
    0.09
     Borough
    0.09
    ronic
    0.08
    .helpers
    0.08
    ì²ĺ
    0.08
     Meg
    0.08
    çŁ³èĨı
    0.08
    Activations Density 0.037%

    No Known Activations