© 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. 32892
    Prev
    Next
    INDEX
    Explanations

    agreement or proposal

    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
    ç®Ĺ
    -0.10
    人å±ħ
    -0.09
    istar
    -0.09
    æĴ¥
    -0.08
    å»Ĵ
    -0.08
    ä¹ī
    -0.08
    缮çĿ¹
    -0.08
    ä¸¥æł¼æĮīçħ§
    -0.08
    ç§ijåѦæĬĢæľ¯
    -0.08
    ä½ıåľ¨
    -0.08
    POSITIVE LOGITS
    åįıè®®
    0.11
    æı¡æīĭ
    0.11
    æĶ¾å¼ĥ
    0.10
    åĩºåı£
    0.10
    è¾¾æĪIJ
    0.10
    åĮĸ解
    0.10
    çŃ¾ä¸ĭ
    0.09
    åįıåķĨ
    0.09
    åĮħ
    0.09
    ä»Ģä¹ĪåİŁåĽł
    0.09
    Activations Density 0.062%

    No Known Activations