© 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. 11155
    Prev
    Next
    INDEX
    Explanations

    user actions and selections

    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
    让èĩªå·±
    -0.09
    emu
    -0.09
    uba
    -0.09
    ega
    -0.09
    éĢĤåIJĪèĩªå·±
    -0.09
    令
    -0.08
     sketch
    -0.08
     wax
    -0.08
     oneself
    -0.08
    iming
    -0.08
    POSITIVE LOGITS
    è·ŁæĪij
    0.12
    è·Łä½ł
    0.11
    åľ¨æĪij
    0.10
    è·ŁæĪij说
    0.10
    ä½Ĩ她
    0.10
    çĪ±ä¸Ĭ
    0.10
    ç³ł
    0.10
    ä»ĸä»¬åľ¨
    0.09
    ä¼ļè§īå¾Ĺ
    0.09
    åľ¨æĪijåĽ½
    0.09
    Activations Density 0.214%

    No Known Activations