© 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. 63358
    Prev
    Next
    INDEX
    Explanations

    captive birds

    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
    é³ŀ
    -0.10
    éĴĵé±¼
    -0.09
    éļıæīĭ
    -0.09
    ç«¿
    -0.09
    .unregister
    -0.08
    碧æ¡ĤåĽŃ
    -0.08
    ä¹±
    -0.08
    æ°ijçĶŁ
    -0.08
    çĥ§
    -0.08
    merged
    -0.08
    POSITIVE LOGITS
    éĽĦ
    0.11
    å¤ĩçĶ¨
    0.10
     eyeb
    0.09
    uite
    0.09
    åIJĮåŁİ
    0.09
    Ñĥма
    0.08
    çĢijå¸ĥ
    0.08
    èIJ¥åķĨ
    0.08
    èĪįå¾Ĺ
    0.08
    hint
    0.08
    Activations Density 0.063%

    No Known Activations