© 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. 56401
    Prev
    Next
    INDEX
    Explanations

    by followed by name

    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
    ä¸į论æĺ¯
    -0.08
    è¿ĻæĶ¯
    -0.08
    欹
    -0.08
    éĤĵå°ı
    -0.08
    è¿Ļåľº
    -0.08
    è
    -0.08
    æµģ转
    -0.08
    æīĢè°ĵ
    -0.08
    彪
    -0.08
    ç§ijçłĶéĻ¢
    -0.08
    POSITIVE LOGITS
    ç»Ĭ
    0.10
    Unnamed
    0.09
     bona
    0.09
    iltr
    0.09
    akit
    0.08
    ivet
    0.08
     clearInterval
    0.08
    \"",↵
    0.08
    延
    0.08
    ä½Ĩä¸įéĻIJäºİ
    0.08
    Activations Density 0.027%

    No Known Activations