© 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. 35311
    Prev
    Next
    INDEX
    Explanations

    food preparation and states

    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
    /OR
    -0.10
    幺
    -0.10
    ç§ijæķĻ
    -0.10
    çīĩåŃIJ
    -0.09
    æ¬ł
    -0.09
    ä¸ĢéĹ´
    -0.09
    çļĦ家åºŃ
    -0.09
    å¸ĤæķĻèĤ²
    -0.09
    家åºŃ
    -0.09
    hare
    -0.09
    POSITIVE LOGITS
    epend
    0.09
    庥
    0.09
    马
    0.08
    æĨ¾
    0.08
    /respond
    0.08
    ouri
    0.08
    åĺī
    0.08
    ised
    0.08
    unsch
    0.08
    æħķ
    0.08
    Activations Density 0.342%

    No Known Activations