© 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. 7039
    Prev
    Next
    INDEX
    Explanations

    functions, land, food, content, files, terms, traits, characters, ologies, data

    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
    è¿ĺæľīä¸Ģ个
    -0.09
    ilton
    -0.09
    åĽŀäºĭ
    -0.09
    ฯ
    -0.09
    å»īä»·
    -0.09
    ä¸ĭæīĭ
    -0.08
    _ASYNC
    -0.08
     Сов
    -0.08
    åĿ¤
    -0.08
    misc
    -0.08
    POSITIVE LOGITS
     whose
    0.12
    æĹ¢èĥ½
    0.10
    whose
    0.10
     اÙĦتÙĬ
    0.09
     that
    0.09
    æľīä¸Ģå®ļ
    0.09
    å±ŀäºİ
    0.08
     unfamiliar
    0.08
     اÙĦØ°ÙĬ
    0.08
    _that
    0.08
    Activations Density 0.743%

    No Known Activations