© 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. 54581
    Prev
    Next
    INDEX
    Explanations

    decrease or stop

    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
     Anything
    -0.09
    åĩ¡æĺ¯
    -0.09
    注å®ļ
    -0.09
    PFN
    -0.09
    æľ¬æĿ¥å°±
    -0.08
    åĩ¡
    -0.08
    Anything
    -0.08
    毫ä¸į
    -0.08
    첨
    -0.08
    å¾Ĺä¸įåĪ°
    -0.08
    POSITIVE LOGITS
    ä¸įä¼ļåĨį
    0.18
    ä¸įåĨį
    0.15
    ä¸įèĩ³äºİ
    0.12
    æĢ»ç®Ĺ
    0.12
    为æŃ¢
    0.12
    ä¸įåĨįæĺ¯
    0.11
    èIJ½ãģ¡çĿĢ
    0.10
     hẳn
    0.10
    æħ¢æħ¢
    0.10
     ÑĥдалоÑģÑĮ
    0.10
    Activations Density 0.101%

    No Known Activations