© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35876
    Prev
    Next
    INDEX
    Explanations

    practice makes perfect, is worth, come true

    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
     slick
    -0.09
    exion
    -0.08
    amar
    -0.08
    èĸ¨
    -0.08
    _iff
    -0.08
    御
    -0.08
    .RESET
    -0.08
    èľĥ
    -0.08
    LOGGER
    -0.08
    æ´Ĺ
    -0.08
    POSITIVE LOGITS
    æĬĬæĪij
    0.09
    åĢ¼å¾Ĺ
    0.09
    ä¼´
    0.09
    éħ¸
    0.09
    ä»·åĢ¼
    0.09
    é¢Ħå®ļ
    0.09
    ä¸ĩéĩĮ
    0.08
    è´²
    0.08
    æľīæīĢ
    0.08
    æ¥
    0.08
    Activations Density 0.022%

    No Known Activations