© 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. 49526
    Prev
    Next
    INDEX
    Explanations

    sum of

    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
    横
    -0.10
     EACH
    -0.09
    åĮ¡
    -0.09
    èĢģçīĮ
    -0.09
    èĢIJçĶ¨
    -0.09
    帽åŃIJ
    -0.09
    æ©«
    -0.09
    寧
    -0.09
    gel
    -0.08
    åĻ¨åħ·
    -0.08
    POSITIVE LOGITS
    æīĢæľī
    0.11
    ãģĻãģ¹ãģ¦
    0.10
    æĪijåĴĮ
    0.10
    两个
    0.09
     all
    0.09
    æīĢæľīçļĦ
    0.09
     Swiss
    0.09
    ä¸Ģç³»åĪĹ
    0.08
    驯
    0.08
    è¿Ļè¾ĪåŃIJ
    0.08
    Activations Density 0.164%

    No Known Activations