© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8499
    Prev
    Next
    INDEX
    Explanations

    by default

    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
    çļĦç¡®æĺ¯
    -0.10
    åįģæĿ¡
    -0.09
    å¤ĩæ¡Ī
    -0.09
    符åIJĪæĿ¡ä»¶
    -0.09
    åįģåĪĨéĴŁ
    -0.09
    åįģåĩłä¸ª
    -0.09
    ä¸īæĿ¡
    -0.09
    èĩªæľī
    -0.08
    æĬ¥æ¡Ī
    -0.08
    .deploy
    -0.08
    POSITIVE LOGITS
     default
    0.15
    é»ĺ认
    0.13
    default
    0.13
     é»ĺ认
    0.12
    (default
    0.11
    -default
    0.10
    ï¼Įé»ĺ认
    0.10
    æŶè£ħ
    0.10
    .DEFAULT
    0.10
    	default
    0.10
    Activations Density 0.044%

    No Known Activations