© 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. 36448
    Prev
    Next
    INDEX
    Explanations

    baseball statistics

    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
    æĺŁ
    -0.09
    æķ£
    -0.09
    æ·¤
    -0.09
    ç¯Ĩ
    -0.08
    ä¸įæŃ»
    -0.08
    UTION
    -0.08
    è§IJ
    -0.08
    ä¸ĢæĹ¥
    -0.08
    cache
    -0.08
    è¿Ľåľº
    -0.07
    POSITIVE LOGITS
    å§ŀ
    0.10
     Chall
    0.09
    lich
    0.09
    YST
    0.09
     ula
    0.09
    mond
    0.09
    PELL
    0.09
    -caption
    0.09
    nels
    0.09
    è¯ķéªĮåĮº
    0.09
    Activations Density 0.075%

    No Known Activations