© 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. 54630
    Prev
    Next
    INDEX
    Explanations

    team names and player surnames

    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
    è¯ı
    -0.10
    åIJİæŀľ
    -0.09
    缼è¡Į
    -0.09
    常çĶ¨
    -0.09
    åIJİåĨį
    -0.09
    æķķ
    -0.09
    æ²Ļ滩
    -0.08
     extr
    -0.08
    åī¥å¤º
    -0.08
    uger
    -0.08
    POSITIVE LOGITS
    .har
    0.09
    પ
    0.09
    æĬ»
    0.08
    .Native
    0.08
    åĩºéģĵ
    0.08
    åĮºç®¡å§Ķä¼ļ
    0.08
    tractor
    0.08
    trä
    0.08
    åİŁæłĩé¢ĺ
    0.08
    traction
    0.08
    Activations Density 0.020%

    No Known Activations