© 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. 20012
    Prev
    Next
    INDEX
    Explanations

    pulse wave analysis

    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
    èĩªè´Ł
    -0.09
    迷人
    -0.09
    manent
    -0.08
    åĮ¡
    -0.08
    é»ĺå¥ij
    -0.08
    æ¢ĵ
    -0.08
    ä¿®å¤į
    -0.08
    æĭ¿åĩº
    -0.08
    æ¼ķ
    -0.08
    รà¸ĵ
    -0.08
    POSITIVE LOGITS
    è¡Ģåİĭ
    0.10
    ÑĢеб
    0.10
     Sheriff
    0.10
    åĿIJ
    0.09
    è¡Ģç³ĸ
    0.09
     волн
    0.09
     Crest
    0.09
    åĽ´
    0.09
    anko
    0.09
    ä¹İ
    0.08
    Activations Density 0.168%

    No Known Activations