© 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. 61151
    Prev
    Next
    INDEX
    Explanations

    slight change or difference

    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
    ãģĦãģĨ
    -0.09
    wards
    -0.09
    istrate
    -0.09
    é©Ń
    -0.09
    oon
    -0.09
    èĻ±
    -0.09
    èµ·æĿ¥
    -0.08
    ĸ
    -0.08
    æĸ½èĤ¥
    -0.08
    ä¸Ģå¥Ĺ
    -0.08
    POSITIVE LOGITS
    emente
    0.11
    ly
    0.11
     обÑĢазом
    0.11
     breeze
    0.11
    LY
    0.11
    ynet
    0.10
    est
    0.10
    쿵
    0.10
    æĦıä¹īä¸ĬçļĦ
    0.10
    ships
    0.09
    Activations Density 0.006%

    No Known Activations