© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21020
    Prev
    Next
    INDEX
    Explanations

    able to provide

    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
    为æѤ
    -0.09
    å°±æѤ
    -0.08
    çĶ¨äºĨ
    -0.08
    ottage
    -0.08
     buggy
    -0.08
    ä¹ĭæīĢ以
    -0.08
    çĶ±äºİ
    -0.08
    æĺ¯ä¸ª
    -0.08
    naments
    -0.08
    èIJ½
    -0.08
    POSITIVE LOGITS
    å¾Ĺ以
    0.13
    æģ¶éŃĶ
    0.12
    便åı¯
    0.12
    åıĺå¾ĹæĽ´åĬł
    0.11
    æĽ´å¥½åľ°
    0.11
    建ç«ĭèµ·
    0.11
    åıĺå¾Ĺ
    0.10
    ä¸įä»ħåı¯ä»¥
    0.10
    ä¸ĢæŃ¥æŃ¥
    0.10
    åıĺæĪIJ
    0.10
    Activations Density 0.148%

    No Known Activations