© 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. 1282
    Prev
    Next
    INDEX
    Explanations

    honorary titles and ambassadors

    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
    ç«ŀä»·
    -0.10
    몰
    -0.10
    泯
    -0.09
     ÑģÑĤоим
    -0.09
    åħ¥åĽ´
    -0.09
    enic
    -0.09
    西æ´ĭ
    -0.09
    æ¯Ľæ³½
    -0.09
     Annotation
    -0.09
    getElement
    -0.09
    POSITIVE LOGITS
     honorary
    0.11
    ç»Ī身
    0.11
    ikon
    0.11
    åIJįèªī
    0.11
    åĢĻ
    0.10
    orary
    0.10
    é¦ĸä½į
    0.09
    æ°¸ä¹ħ
    0.09
    侯
    0.09
    æįIJèµł
    0.09
    Activations Density 0.104%

    No Known Activations