© 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. 5755
    Prev
    Next
    INDEX
    Explanations

    gather for events

    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
    æľ¬å±Ĭ
    -0.09
    延ç»Ń
    -0.08
    ouro
    -0.08
    èĢĮéĿŀ
    -0.08
    沿线
    -0.08
    åŃĺæ´»
    -0.08
    äºĮåŃĹ
    -0.08
    羸
    -0.08
    çĶŁæ¶¯
    -0.08
    ä»ĭåħ¥
    -0.08
    POSITIVE LOGITS
    åľ¨ä¸Ģèµ·
    0.14
    åĽ´
    0.10
    åĪ·
    0.09
    -sama
    0.09
    ä¸Ģå¤Ħ
    0.09
    æ³ķ令
    0.09
    æłĩæĿĨ
    0.09
    èµ·ä¾Ĩ
    0.08
    èµ·æĿ¥
    0.08
    çļĦèĥĮåIJİ
    0.08
    Activations Density 0.044%

    No Known Activations