© 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. 50843
    Prev
    Next
    INDEX
    Explanations

    into one

    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
    çĻ»åľº
    -0.09
    å·¥ä½ľæĬ¥åijĬ
    -0.08
    çļĦè·¯ä¸Ĭ
    -0.08
    çļĦ主é¢ĺ
    -0.08
    æĪijè¦ģ
    -0.08
    ç´IJ
    -0.08
    å¼ĢéŨ
    -0.08
    à¹ĩà¸ļ
    -0.08
    ÑıÑĤ
    -0.08
    èĤ
    -0.08
    POSITIVE LOGITS
     into
    0.28
    into
    0.23
    Into
    0.22
     Into
    0.22
     INTO
    0.20
     vÃło
    0.19
    _into
    0.19
    .into
    0.17
    æĪIJ
    0.15
    æĪIJ为ä¸Ģ个
    0.12
    Activations Density 0.230%

    No Known Activations