© 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. 19111
    Prev
    Next
    INDEX
    Explanations

    administrative center/seat

    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
    弯
    -0.10
    éĻµ
    -0.09
    å¾Ĵ
    -0.09
    quate
    -0.09
    icode
    -0.08
     Synd
    -0.08
    漫
    -0.08
     плоÑħо
    -0.08
     ná»ģn
    -0.08
     Snyder
    -0.08
    POSITIVE LOGITS
    ä¸Ńå¿ĥ
    0.20
     center
    0.17
    CENTER
    0.16
    管çIJĨä¸Ńå¿ĥ
    0.15
    _center
    0.15
    .center
    0.15
     centers
    0.15
    Center
    0.14
     centre
    0.14
    center
    0.14
    Activations Density 0.058%

    No Known Activations