© 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. 21348
    Prev
    Next
    INDEX
    Explanations

    United States locations

    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¸ŃåĽ½äºº
    -0.09
    è¿Ļ个åIJįåŃĹ
    -0.08
    oken
    -0.08
     stump
    -0.08
    raries
    -0.08
    è¿Ļ个è¯į
    -0.08
    æł¼å°Ķ
    -0.08
    æ¹Ľ
    -0.08
    åħ¶æ¬¡
    -0.08
    arger
    -0.07
    POSITIVE LOGITS
    -Israel
    0.10
     thủ
    0.10
    æľ¬åľŁ
    0.10
    åħ¨ç¨ĭ
    0.09
    åģļ大
    0.09
    å¢ĥåĨħ
    0.09
    åįļ主
    0.09
    upo
    0.09
    ZN
    0.09
    edelta
    0.09
    Activations Density 0.310%

    No Known Activations