© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20156
    Prev
    Next
    INDEX
    Explanations

    UEFA activations

    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
    çªģåĽ´
    -0.10
    lessly
    -0.10
    åħ¢
    -0.09
    ultz
    -0.09
    ëĭĿ
    -0.09
    bons
    -0.09
    meld
    -0.09
    aic
    -0.09
    à¸ģระà¸Ĺ
    -0.09
     hã
    -0.08
    POSITIVE LOGITS
    ivity
    0.12
    禳
    0.09
    iator
    0.09
    ãģĦãģªãģĦ
    0.09
    opath
    0.09
    ãģİ
    0.08
    åīįä¸ī
    0.08
     pals
    0.08
    çı©
    0.08
    ä¸ĢæŶ
    0.08
    Activations Density 0.006%

    No Known Activations