© 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. 55953
    Prev
    Next
    INDEX
    Explanations

    how to

    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
    æĤ£èĢħçļĦ
    -0.10
    æľīä¸Ģå®ļçļĦ
    -0.09
    ä½ij
    -0.08
    éķĸ
    -0.08
    è¾ĥ大çļĦ
    -0.08
    æŁ¥çľĭåħ¨æĸĩ
    -0.08
    æIJģ
    -0.08
    ä¸Ĭçľĭ
    -0.08
    DSL
    -0.07
    ç¼´
    -0.07
    POSITIVE LOGITS
    å¦Ĥä½ķ
    0.22
    å¦Ĥä½ķåİ»
    0.20
     how
    0.17
    æĢİæł·
    0.17
    æĢİä¹Ī
    0.16
    该å¦Ĥä½ķ
    0.15
     cómo
    0.15
    该æĢİä¹Ī
    0.14
    how
    0.14
    æĢİ麼
    0.13
    Activations Density 0.148%

    No Known Activations