© 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. 22488
    Prev
    Next
    INDEX
    Explanations

    rural and wilderness settings

    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
    er
    -0.10
    é¢Ĩ导干éĥ¨
    -0.09
    ä½Ĩä¸įéĻIJäºİ
    -0.09
    ãģĦãĤĭ
    -0.09
    æ°¸ä¸į
    -0.08
    æĦıä¹īä¸ĬçļĦ
    -0.08
    海峡
    -0.08
    ä¸ĸä¸Ĭ
    -0.08
    idable
    -0.08
    ä¸Ģæľ¬ä¹¦
    -0.08
    POSITIVE LOGITS
    èĶĵ
    0.10
    çĶº
    0.09
    è®©æĽ´å¤ļ
    0.09
    人士
    0.09
    ÑĤай
    0.08
    enser
    0.08
    presso
    0.08
    hä
    0.08
    orf
    0.08
    \Php
    0.08
    Activations Density 0.008%

    No Known Activations