© 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. 34257
    Prev
    Next
    INDEX
    Explanations

    au.com

    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
    çĵ´
    -0.09
    丸
    -0.09
    éĺ»æĮ¡
    -0.09
    _DOM
    -0.09
    ermo
    -0.09
    reta
    -0.09
    avis
    -0.09
    èĵ¦
    -0.09
    å®ĺæĸ¹å¾®ä¿¡
    -0.09
    AGO
    -0.09
    POSITIVE LOGITS
    ä¸Ńå°ı
    0.09
    mes
    0.09
     Synd
    0.08
     اÙĦدر
    0.08
    è¿ĩæĿ¥
    0.08
     IDC
    0.08
    åĴĮåıijå±ķ
    0.08
    scopes
    0.08
    ожно
    0.08
    urers
    0.08
    Activations Density 0.049%

    No Known Activations