© 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. 54072
    Prev
    Next
    INDEX
    Explanations

    articles after 'the'

    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
    /from
    -0.11
    çļĦ人æĿ¥è¯´
    -0.10
    çݩ家æĿ¥è¯´
    -0.10
    æ¯ıä¸Ģ个人
    -0.10
    ç§įç§į
    -0.09
    ä¼ĹæīĢåij¨çŁ¥
    -0.09
    inder
    -0.09
    说éģĵ
    -0.08
    çļĦä¸Ģåijĺ
    -0.08
    åħ¶ä»ĸçļĦ
    -0.08
    POSITIVE LOGITS
     sooner
    0.12
     aim
    0.11
    缮çļĦæĺ¯
    0.10
     goal
    0.10
    大éĥ¨åĪĨ
    0.10
    éĩįå¿ĥ
    0.10
    ç¡®
    0.10
    goal
    0.10
    å®ĥ
    0.10
    两èĢħ
    0.09
    Activations Density 0.422%

    No Known Activations