© 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. 33393
    Prev
    Next
    INDEX
    Explanations

    legal decisions and citations

    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
    èĦı
    -0.08
    ç¾Ķ
    -0.08
     paran
    -0.08
    è¨ĪåĬĥ
    -0.08
    åħ³å¿ĥ
    -0.08
    åĿIJçĿĢ
    -0.08
    çIJĨæĻº
    -0.07
    æĭįæijĦ
    -0.07
    æĮ¨
    -0.07
    éĻ°
    -0.07
    POSITIVE LOGITS
     ÐIJлекÑģан
    0.09
    à¹Ĥà¸Ī
    0.09
    论è¯ģ
    0.08
    -shopping
    0.08
    æłĩå¿ĹæĢ§
    0.08
    éĹ®çŃĶ
    0.08
    éĤ£ä½į
    0.08
    ää
    0.08
    /Runtime
    0.08
    ä¸įéĻIJ
    0.08
    Activations Density 0.090%

    No Known Activations