© 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. 18537
    Prev
    Next
    INDEX
    Explanations

    asking for public input

    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
    éĶŁ
    -0.09
    sed
    -0.08
    nings
    -0.08
    æľīçĽĬ
    -0.08
    延伸
    -0.08
    æĪijèĩªå·±
    -0.08
    shoot
    -0.08
    é¦Ĺ
    -0.08
    çĪ±åĽ½ä¸»ä¹ī
    -0.08
    å§ĭ建
    -0.07
    POSITIVE LOGITS
    æĥ³çŁ¥éģĵ
    0.12
    mary
    0.10
    ãĢĴ
    0.09
    æīĵæī°
    0.09
    è¯ķåĽ¾
    0.09
    伸æīĭ
    0.09
     Synopsis
    0.09
    注æĦı
    0.09
    è¿«åĪĩ
    0.09
    CADE
    0.09
    Activations Density 0.018%

    No Known Activations