© 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. 34334
    Prev
    Next
    INDEX
    Explanations

    introductions and explanations

    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
    åŃĺéĩı
    -0.09
    æīĺ管
    -0.09
    èĵĿåĽ¾
    -0.09
    åıªè§ģ
    -0.08
    ¾ç¤º
    -0.08
    ctors
    -0.08
    éģĹçķĻ
    -0.08
    ä¼łåĩº
    -0.08
    è¿ŀäºij
    -0.08
    ãĤªãĤ¹
    -0.08
    POSITIVE LOGITS
    åľ¨ä¸ĢæĹģ
    0.13
    (Tile
    0.11
    éĿ©
    0.11
    說æĺİ
    0.11
    说æĺİ
    0.11
    讲解
    0.10
    ä»ĭç»į说
    0.10
    解éĩĬ
    0.10
    讲述äºĨ
    0.10
    åİĨåı²æĸĩåĮĸ
    0.10
    Activations Density 0.114%

    No Known Activations