© 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. 1162
    Prev
    Next
    INDEX
    Explanations

    playground

    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
    ities
    -0.11
    æħĮ
    -0.10
    ç½ij讯
    -0.10
    омеÑĢ
    -0.10
    lessly
    -0.10
    æķ´åĢĭ
    -0.10
    åģļä¸įåĪ°
    -0.09
    TING
    -0.09
    pane
    -0.09
    æķ´ä¸ª
    -0.09
    POSITIVE LOGITS
    çİ©èĢį
    0.11
    onne
    0.10
    åĿĿ
    0.09
    综åIJĪä½ĵ
    0.09
    åŃ©ç«¥
    0.09
    íĺģ
    0.09
    æĢ»çĽij
    0.09
    ç¨ļ
    0.08
    ersen
    0.08
    æĩ¿
    0.08
    Activations Density 0.009%

    No Known Activations