© 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. 55990
    Prev
    Next
    INDEX
    Explanations

    file names and code snippets

    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
     lak
    -0.10
    ç´«èī²
    -0.09
    ç¿Ĭ
    -0.09
    管çIJĨ人åijĺ
    -0.09
    æľºéģĩ
    -0.09
     Serbian
    -0.08
    é¦ħ
    -0.08
    è´¨éĩıéĹ®é¢ĺ
    -0.08
    便æ°ij
    -0.08
    æ³¼
    -0.08
    POSITIVE LOGITS
     اÙĦÙĬÙħÙĨ
    0.11
     Yemen
    0.10
    åģ¶
    0.10
     اÙĦØŃÙĪØ«
    0.09
    æ±²
    0.09
    urch
    0.09
    éĹª
    0.09
     اÙĦÙħÙĪ
    0.09
     Patton
    0.09
    dispatcher
    0.09
    Activations Density 0.023%

    No Known Activations