© 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. 32518
    Prev
    Next
    INDEX
    Explanations

    added version or also works

    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
    å®ĺ宣
    -0.10
    .OutputStream
    -0.09
    gd
    -0.08
    /Instruction
    -0.08
    å°ıåŀĭ
    -0.08
    å®ģæĦ¿
    -0.08
    elu
    -0.08
    åij¨åĽ´çļĦ
    -0.08
    çļĵ
    -0.08
    éķ¿åŁİ
    -0.08
    POSITIVE LOGITS
    åĪĿæŃ¥
    0.11
    æĪijä¼ļ
    0.10
    è²Ĥ
    0.10
    é£ĺ
    0.09
    æķ´åIJĪ
    0.09
    cura
    0.09
    让大家
    0.09
    ä¸įå®ļ
    0.09
    åħ¼å®¹
    0.09
    ç§ģ人
    0.08
    Activations Density 0.250%

    No Known Activations