© 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. 33587
    Prev
    Next
    INDEX
    Explanations

    sources of information

    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
    æĴij
    -0.09
     exclusive
    -0.09
     mim
    -0.09
    ikal
    -0.09
     Weston
    -0.08
    ç¬ij容
    -0.08
    ä»ĵ
    -0.08
    _far
    -0.08
    exclusive
    -0.08
    lord
    -0.08
    POSITIVE LOGITS
    æĦıæĥ³ä¸įåĪ°
    0.13
     sources
    0.13
    æĿ¥æºIJ
    0.11
     иÑģÑĤоÑĩ
    0.11
    à¹ģหล
    0.11
    æĥ³ä¸įåĪ°
    0.11
    æ¸łéģĵ
    0.11
    æºIJæ³ī
    0.11
     Sources
    0.10
    åIJĦ个æĸ¹éĿ¢
    0.10
    Activations Density 0.084%

    No Known Activations