© 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. 33884
    Prev
    Next
    INDEX
    Explanations

    building-street-suite-floor

    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
    æĸĩåĮĸä¼łæĴŃ
    -0.09
    reak
    -0.08
    æī©å¼ł
    -0.08
    ylum
    -0.08
    åľ°çĭ±
    -0.08
    é£ı
    -0.08
    æĬ¥è®°èĢħ
    -0.08
    ç½ij讯
    -0.08
     жел
    -0.08
    pras
    -0.08
    POSITIVE LOGITS
    æĹłæķĪ
    0.09
    å½Ĵå±ŀ
    0.08
    fant
    0.08
    ãĤ¹ãĤ¯
    0.08
    楹
    0.08
    coop
    0.08
     siege
    0.08
    illes
    0.08
    æľµ
    0.08
    éĴ°
    0.08
    Activations Density 0.046%

    No Known Activations