© 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. 11808
    Prev
    Next
    INDEX
    Explanations

    content warnings and disclaimers

    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
    åļ
    -0.11
     Hubb
    -0.10
    nect
    -0.09
    ewise
    -0.09
    .Properties
    -0.09
    æľĹ
    -0.08
    ä¸Ģé¢Ĺ
    -0.08
    çĿ¥
    -0.08
    ä¸Ģä½ĵ
    -0.08
    æ³®
    -0.08
    POSITIVE LOGITS
    æļ´åĬĽ
    0.11
    abo
    0.09
    è¡Ģèħ¥
    0.09
    åİĮæģ¶
    0.09
    å¿ĥçģµ
    0.09
    ä¸įåłª
    0.09
    hen
    0.09
    æ¿ĢçĥĪçļĦ
    0.09
    纪
    0.09
    getContent
    0.09
    Activations Density 0.147%

    No Known Activations