© 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. 35040
    Prev
    Next
    INDEX
    Explanations

    European Tour tournaments

    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
    座ä½į
    -0.09
    ä»İå°ı
    -0.09
    ç´łé£Ł
    -0.09
    bow
    -0.08
    è¯ĥ
    -0.08
    èĨĬ
    -0.08
    cen
    -0.08
    ÙĦب
    -0.08
    ä¸įæŃ»
    -0.08
    ouncy
    -0.08
    POSITIVE LOGITS
     reps
    0.10
    гаÑĢ
    0.10
    OSE
    0.09
    못
    0.09
     sür
    0.09
    \Extension
    0.09
    åĿĽ
    0.09
    çĶ·åŃIJ
    0.08
    egt
    0.08
    æĻķ
    0.08
    Activations Density 0.040%

    No Known Activations