© 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. 58303
    Prev
    Next
    INDEX
    Explanations

    translation and localization

    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
    åįij
    -0.09
    éģı
    -0.09
    æ®ĭéħ·
    -0.09
    缴æĴŃ
    -0.09
    ÑģÑĤ
    -0.09
    \Plugin
    -0.08
    岩
    -0.08
    注æĺİæĿ¥æºIJ
    -0.08
    ĵåIJį
    -0.08
    çľĭçĶµè§Ĩ
    -0.08
    POSITIVE LOGITS
    åĽ½éĻħå¸Ĥåľº
    0.12
    è¯ij
    0.11
    ç¿»è¯ij
    0.11
     translations
    0.11
    translations
    0.11
    /locale
    0.10
    稿
    0.10
    Localization
    0.10
     translation
    0.10
    éĴ³
    0.10
    Activations Density 0.222%

    No Known Activations