© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22062
    Prev
    Next
    INDEX
    Explanations

    Golden Eagles

    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
    ÑĢÑĥÑģ
    -0.09
    subpackage
    -0.09
    bung
    -0.09
    оÑĢа
    -0.08
    autor
    -0.08
    anes
    -0.08
    è¡¥
    -0.08
     chÃŃ
    -0.08
    ikan
    -0.08
    顺
    -0.08
    POSITIVE LOGITS
    ä¹ĭ乡
    0.10
    çĭ
    0.10
    们
    0.10
    ä¼łåªĴ
    0.09
    éĢ»
    0.09
    Refs
    0.09
    æĺĨä»ij
    0.09
    骡
    0.09
    æİĢ
    0.09
    建çŃijå·¥ç¨ĭ
    0.08
    Activations Density 0.076%

    No Known Activations