© 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. 4779
    Prev
    Next
    INDEX
    Explanations

    focus on

    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
    人å¿ĥ
    -0.10
     Tre
    -0.09
    лин
    -0.09
    atal
    -0.08
    alia
    -0.08
    ä¸įæĺİ
    -0.08
    icha
    -0.08
    SR
    -0.08
     fet
    -0.08
    å¯ĤéĿĻ
    -0.08
    POSITIVE LOGITS
    ä¸ĵ注äºİ
    0.11
    ä¸ĵ注
    0.11
    æij¹
    0.10
    ascript
    0.10
     focus
    0.09
    éĮ¾
    0.09
    éļľ
    0.09
    åĴĮæĶ¯æĮģ
    0.09
     háºŃu
    0.09
    dess
    0.09
    Activations Density 0.025%

    No Known Activations