© 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. 57221
    Prev
    Next
    INDEX
    Explanations

    better understand, assess, define, navigate

    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
    cente
    -0.10
    anke
    -0.10
    _rating
    -0.09
    ä¸įåİ»
    -0.09
    ç¨įå¾®
    -0.09
    æľĢç»Ī
    -0.09
    ç¨į
    -0.08
    ä¸Ģæīĭ
    -0.08
    stream
    -0.08
    åħīæĺİ
    -0.08
    POSITIVE LOGITS
    èĩ³æĸ¼
    0.10
    åŃIJéĩĮ
    0.10
    åľ°ä¸Ń
    0.10
    hone
    0.09
     ourselves
    0.09
    ä¼łåĩº
    0.09
    ãĤ
    0.09
    ç½ijç»ľä¼łæĴŃ
    0.09
    heel
    0.09
     ÑģебÑı
    0.09
    Activations Density 0.017%

    No Known Activations