© 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. 17857
    Prev
    Next
    INDEX
    Explanations

    first step

    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
    æ¡¢
    -0.09
    ç©¿
    -0.09
    wear
    -0.09
    çıł
    -0.09
    ç»ĪçĶŁ
    -0.08
     Bomb
    -0.08
    ÑĢÑĥг
    -0.08
    Ptr
    -0.08
    SHOT
    -0.08
    æĹģ
    -0.08
    POSITIVE LOGITS
    å°±æĺ¯è¦ģ
    0.11
    æĦł
    0.10
    çĿĢæīĭ
    0.10
    æĪij们è¦ģ
    0.10
    è¿Īåĩº
    0.09
    ä»»ä½ķå½¢å¼ı
    0.09
    第ä¸ĢæŃ¥
    0.09
    è¿ĺæĺ¯è¦ģ
    0.09
    ä¸ĢæŃ¥
    0.09
    edBy
    0.09
    Activations Density 0.031%

    No Known Activations