© 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. 51390
    Prev
    Next
    INDEX
    Explanations

    wildlife sculpture

    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
    ç²ĺ
    -0.10
    é»ı
    -0.09
    apo
    -0.09
    çĻ½éĽª
    -0.09
    æī³
    -0.09
    æ´Ĺ
    -0.09
    å¼Ī
    -0.09
    å¥ı
    -0.09
    çĭ¬
    -0.08
    .prepare
    -0.08
    POSITIVE LOGITS
    astr
    0.10
    çľ¼åħī
    0.09
    丰æĶ¶
    0.09
    lags
    0.08
    Gary
    0.08
    ä¼łç»Ł
    0.08
    å¹¢
    0.08
    æijĦ
    0.08
    Leap
    0.08
    åŀĽ
    0.08
    Activations Density 0.179%

    No Known Activations