© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 20665
    Prev
    Next
    INDEX
    Explanations

    Bashar al-Assad, cerebral white matter

    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
    ridge
    -0.09
    æ°´è´¨
    -0.09
    份
    -0.08
    æŃ¥æŃ¥
    -0.08
    ï¸
    -0.08
    ç´¢åıĸ
    -0.08
    é«ĺ涨
    -0.08
    ards
    -0.08
    lopedia
    -0.08
    ç°ĩ
    -0.08
    POSITIVE LOGITS
    ural
    0.09
    IME
    0.09
    èĶ«
    0.09
    haus
    0.09
    nt
    0.09
    èº²åľ¨
    0.09
    omid
    0.08
    hood
    0.08
    æľįåĬ¡ä½ĵç³»
    0.08
    urally
    0.08
    Activations Density 0.002%

    No Known Activations