© 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. 50051
    Prev
    Next
    INDEX
    Explanations

    hope you / this / to

    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
    究竣æĺ¯
    -0.09
    æĢı
    -0.09
    ä¸ĢåIJij
    -0.08
    åĽ¢éķ¿
    -0.08
    ible
    -0.08
    æĽĿåħī
    -0.08
    çļĦä¸ĸçķĮ
    -0.08
    art
    -0.08
    9
    -0.08
    ire
    -0.08
    POSITIVE LOGITS
    unist
    0.10
    adero
    0.09
    ooks
    0.09
    иг
    0.09
    APER
    0.09
    æĹłæīĢ
    0.09
    NSE
    0.09
    æ¯ı个人çļĦ
    0.09
    oth
    0.09
    è¿Ļ对äºİ
    0.08
    Activations Density 0.020%

    No Known Activations