© 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. 58268
    Prev
    Next
    INDEX
    Explanations

    asking for understanding or help

    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
    æ®Ĭ
    -0.09
    ç»ĦåĽ¢
    -0.09
    оказ
    -0.09
    .Bot
    -0.08
    åŁµ
    -0.08
    .ua
    -0.08
    Ñĥв
    -0.08
    CTYPE
    -0.08
    ä¼ŀ
    -0.08
    ---@
    -0.08
    POSITIVE LOGITS
    èĢIJå¿ĥ
    0.10
    ä¸Ģä¼ļ
    0.10
    è·ŁæĪij说
    0.10
    æħ¢æħ¢
    0.09
    æĪij说
    0.09
    è¿IJèIJ¥ç®¡çIJĨ
    0.09
    ä¸Ģä¼ļåĦ¿
    0.09
    æ®ĩ
    0.09
    ambre
    0.08
    è··
    0.08
    Activations Density 0.076%

    No Known Activations