© 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. 61776
    Prev
    Next
    INDEX
    Explanations

    claims and criticism

    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
    人äºĭ
    -0.11
    èµ·æĿ¥äºĨ
    -0.10
     Lover
    -0.09
    èĻ½
    -0.09
    /Runtime
    -0.09
    æĹ¶ä»£çļĦ
    -0.09
     GLsizei
    -0.09
    _RUNTIME
    -0.09
     Cooler
    -0.09
    æĥ³ä¸įåĪ°
    -0.09
    POSITIVE LOGITS
    éĤ£æł·
    0.09
    åIJĮæĥħ
    0.08
     fence
    0.08
    ä»ĸæĽ¾
    0.08
    çħ§æĸĻ
    0.08
    è®ĵä»ĸ
    0.08
    éĹ´éļĻ
    0.08
    ä»ĸçļĦ
    0.08
    ä»ĸä¼ļ
    0.08
    ihn
    0.08
    Activations Density 0.124%

    No Known Activations