© 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. 10351
    Prev
    Next
    INDEX
    Explanations

    child's condition

    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
    åĪ°ä½į
    -0.09
    æĪijè¿ĺ
    -0.09
    è¿ĺåľ¨
    -0.09
    æĪijèĩªå·±
    -0.09
    åľ¨ä¸Ģèµ·
    -0.09
     Vac
    -0.09
    ä¸ĵ
    -0.09
    éļıä¹ĭ
    -0.08
    urai
    -0.08
    æĪij对
    -0.08
    POSITIVE LOGITS
    åIJĦèĩªçļĦ
    0.12
    åIJĦèĩª
    0.11
    ä»ĸ们çļĦ
    0.10
     Äijâu
    0.09
    转载请
    0.09
    ueur
    0.09
     their
    0.09
    ников
    0.09
    enta
    0.08
    AMED
    0.08
    Activations Density 0.175%

    No Known Activations