© 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. 1533
    Prev
    Next
    INDEX
    Explanations

    fat, oil, lipid, emulsions, frying

    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
    èĩªæĿ¥
    -0.11
    icum
    -0.10
    åĩ«
    -0.10
    ç³Ĭ
    -0.09
    UMP
    -0.09
    å¤ļéĩį
    -0.09
    laps
    -0.09
    è¹Ń
    -0.08
     Dual
    -0.08
    éĴ©
    -0.08
    POSITIVE LOGITS
    ç»´å°Ķ
    0.11
    ä¸įåĪĨ
    0.09
    å¹´ç»Ī
    0.09
    èµ
    0.08
    æĸĹ
    0.08
    _star
    0.08
    æ¯ķç«Ł
    0.08
    涸
    0.08
    enis
    0.08
    è°ĪåĪ°
    0.08
    Activations Density 0.115%

    No Known Activations