© 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. 17176
    Prev
    Next
    INDEX
    Explanations

    hotels, inns, motels, lodges

    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
    antro
    -0.09
    æ£ļ
    -0.09
    год
    -0.09
    èĭįçĻ½
    -0.09
    æĹłæīĢ
    -0.09
    广åijĬæľįåĬ¡
    -0.09
    æłĿ
    -0.09
    ä»Ĭå¹´
    -0.09
    é£İåIJ¹
    -0.08
    åħ¨æĿij
    -0.08
    POSITIVE LOGITS
    综åIJĪä½ĵ
    0.10
    è¿ŀéĶģ
    0.10
    aru
    0.09
    é©¿
    0.09
     Pass
    0.08
     Asi
    0.08
     hotels
    0.08
    éħĴåºĹ
    0.08
    驱
    0.08
    ahi
    0.08
    Activations Density 0.157%

    No Known Activations