© 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. 27440
    Prev
    Next
    INDEX
    Explanations

    fertilizers, milling, currency, India

    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
    æŁĶ
    -0.10
    LabelText
    -0.09
    é»ĺ
    -0.09
    ä¸ĢæĿ¡
    -0.08
     Athen
    -0.08
    åīª
    -0.08
    åįģåħ«
    -0.08
     доб
    -0.08
    Ads
    -0.07
     ahead
    -0.07
    POSITIVE LOGITS
    ç§ijçłĶéĻ¢æīĢ
    0.12
    å½ķ
    0.09
    è¿Ľåı£
    0.09
    èĭ«
    0.09
    ç±´
    0.09
    åĩºåħ¥å¢ĥ
    0.09
     accord
    0.09
    çĬ¬
    0.09
    纪å½ķ
    0.09
    åĮ®
    0.09
    Activations Density 0.087%

    No Known Activations