© 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. 57321
    Prev
    Next
    INDEX
    Explanations

    sugars and sweetness

    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
    ç§ĭåĨ¬
    -0.11
    æİ¢æµĭ
    -0.09
    apo
    -0.09
    西äºļ
    -0.09
    åĽ¢éķ¿
    -0.08
    åı¯æĥ³
    -0.08
    ë³´
    -0.08
    åıijèµ·
    -0.08
    éºŁ
    -0.08
    æīij
    -0.08
    POSITIVE LOGITS
    åľ¨æ¸¸æĪıä¸Ń
    0.10
    ä¿İ
    0.10
    lier
    0.10
    游æĪıä¸Ń
    0.10
    iness
    0.09
    athing
    0.09
    åħ¨ç¤¾ä¼ļ
    0.09
    èĽĻ
    0.09
    åľ¨çĶŁæ´»ä¸Ń
    0.09
    踮
    0.09
    Activations Density 0.028%

    No Known Activations