© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19970
    Prev
    Next
    INDEX
    Explanations

    available under the terms of license

    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
    被迫
    -0.10
    èĺijèıĩ
    -0.10
     Whe
    -0.10
    èĬĴ
    -0.09
    ä»İä¸Ń
    -0.09
    èİ«
    -0.09
    ç¼ĿéļĻ
    -0.09
    严å¯Ĩ
    -0.09
     Whip
    -0.09
    æ·®åįĹ
    -0.09
    POSITIVE LOGITS
    td
    0.09
     Affero
    0.08
     via
    0.08
     ÑģебÑı
    0.08
    æĹ¢åı¯ä»¥
    0.08
    åĪĽä½ľèĢħ
    0.08
    ned
    0.08
     Guest
    0.08
    _GPIO
    0.08
     thoáng
    0.08
    Activations Density 0.028%

    No Known Activations