© 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. 4934
    Prev
    Next
    INDEX
    Explanations

    biometrics, grade, based, rental, ophthalmologic

    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
    озд
    -0.09
    æĶ¯éħį
    -0.09
    åıĭæĥħéĵ¾æİ¥
    -0.09
    allel
    -0.09
    樱èĬ±
    -0.08
    ÑĤиÑĢ
    -0.08
    äºİæĺ¯
    -0.08
    kening
    -0.08
    è¡Įéķ¿
    -0.08
    Ñģки
    -0.08
    POSITIVE LOGITS
    æ£Ģ
    0.09
    eli
    0.09
    æ¡ħ
    0.08
     Unlimited
    0.08
     SCO
    0.08
    mpp
    0.08
    ç½ijå°ıç¼ĸ
    0.08
    cca
    0.08
    ä¾ł
    0.08
     TODAY
    0.07
    Activations Density 1.200%

    No Known Activations