© 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. 34561
    Prev
    Next
    INDEX
    Explanations

    internet connection, javascript, or control

    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
    poon
    -0.10
    å¼ĭ
    -0.10
    涤
    -0.09
    对人ä½ĵ
    -0.09
    ä»ĭ
    -0.08
    åľ¨æĦı
    -0.08
    ıc
    -0.08
    caps
    -0.08
     Spy
    -0.08
    ını
    -0.08
    POSITIVE LOGITS
    ï¸
    0.08
    ä»Ģä¹Īäºĭæĥħ
    0.08
    roi
    0.08
    ä»ĬæĹ¥
    0.07
     даже
    0.07
    èIJ¥
    0.07
    éĿ¢çĻ½
    0.07
     ê¶
    0.07
    å°ıä¼ĻåŃIJ
    0.07
    ä¸Ģç«Ļ
    0.07
    Activations Density 0.842%

    No Known Activations