© 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. 23319
    Prev
    Next
    INDEX
    Explanations

    Derek Jeter had

    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·ĭ
    -0.10
    ä»Ļ女
    -0.09
    æĿ¥ä¸įåıĬ
    -0.09
    udent
    -0.08
    åĨį说
    -0.08
    atics
    -0.08
    åħ·æľīä¸Ģå®ļ
    -0.08
    å®ŀå¹²
    -0.08
     Perspectives
    -0.08
     perspective
    -0.08
    POSITIVE LOGITS
    anol
    0.10
    羡
    0.09
    åĨĴ
    0.09
    常çĶ¨
    0.09
    opup
    0.09
    _DOT
    0.09
    /vendors
    0.09
     pepp
    0.09
    acted
    0.08
    (CharSequence
    0.08
    Activations Density 0.013%

    No Known Activations