© 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. 32561
    Prev
    Next
    INDEX
    Explanations

    language, country, game, article, event, tool

    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
     ê·¸ë¦¬ê³ł
    -0.08
    istes
    -0.08
    æļ¾
    -0.08
    æĬĬæīĭ
    -0.08
    enso
    -0.08
    edList
    -0.08
    æĸ°å¼Ģ
    -0.08
    UST
    -0.07
    elter
    -0.07
    ä»ħä»ħæĺ¯
    -0.07
    POSITIVE LOGITS
    ä¹ĭä¸Ģ
    0.12
    çĽ¸å¯¹è¾ĥ
    0.11
     пÑĢинÑı
    0.10
    ä»ħ次äºİ
    0.09
    è·ª
    0.09
    容è²Į
    0.09
    ä¸įéĶĻ
    0.09
    à¹Ĥà¸Ľà¸£à¸Ķ
    0.09
    å®ľå±ħ
    0.09
    æĢİ
    0.09
    Activations Density 0.205%

    No Known Activations