© 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. 62562
    Prev
    Next
    INDEX
    Explanations

    ripe, mature, uration

    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
    des
    -0.11
    é»ijçĻ½
    -0.10
    åIJ¸æ¯Ĵ
    -0.10
     Sunrise
    -0.08
     Bout
    -0.08
    baugh
    -0.08
    çļĦæ¯į亲
    -0.08
    建çŃijæĿIJæĸĻ
    -0.08
     Rex
    -0.08
    roman
    -0.08
    POSITIVE LOGITS
    æŶèĬĤ
    0.12
    eters
    0.10
    ä¸Ģ个æĺŁæľŁ
    0.10
    èĥª
    0.10
    æ´
    0.10
    eload
    0.09
    zelf
    0.09
    etail
    0.09
     ripe
    0.09
    ãĤĤãģ®
    0.09
    Activations Density 0.007%

    No Known Activations