© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51453
    Prev
    Next
    INDEX
    Explanations

    locations following "in"

    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
    æĬĬæı¡
    -0.09
    太å°ij
    -0.08
    è¿IJåĬ¨ä¼ļ
    -0.08
    æ»ĭ
    -0.08
     entert
    -0.08
    æķ
    -0.07
     вÑģ
    -0.07
    æ¸Ń
    -0.07
    丸
    -0.07
     exams
    -0.07
    POSITIVE LOGITS
    MSN
    0.10
    _PG
    0.10
    HO
    0.09
     Hoy
    0.09
    ãĥĬãĥ«
    0.09
    ëī´
    0.09
    ấp
    0.09
    æ¿Ĵ临
    0.09
    åĩıåħį
    0.09
     nghiá»ĩp
    0.09
    Activations Density 0.138%

    No Known Activations