© 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. 52800
    Prev
    Next
    INDEX
    Explanations

    poster

    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
    åĢĮ
    -0.10
    Civil
    -0.09
    accounts
    -0.09
    æł¹æľ¬ä¸į
    -0.08
    绩æķĪ
    -0.08
    UDGE
    -0.08
    æĻ¨æĬ¥
    -0.08
    祧
    -0.08
    è¿ĻæĶ¯
    -0.08
    uez
    -0.08
    POSITIVE LOGITS
    å¼łè´´
    0.13
    æµ·æĬ¥
    0.12
    æĴķ
    0.12
     Poster
    0.11
    poster
    0.10
     posters
    0.10
     poster
    0.10
    stry
    0.10
    ä¿ĥéĶĢ
    0.10
    Poster
    0.10
    Activations Density 0.038%

    No Known Activations