© 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. 58437
    Prev
    Next
    INDEX
    Explanations

    call database function

    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
    haven
    -0.09
    èĩªåıij
    -0.09
    åĬŁåĬ³
    -0.09
    èµ°ä¸Ĭ
    -0.09
    elig
    -0.09
    踮
    -0.09
    è²ī
    -0.09
     долж
    -0.09
    ument
    -0.09
    çľ¼åīį
    -0.09
    POSITIVE LOGITS
     attention
    0.11
    éŃĤ
    0.11
    culate
    0.10
    igraphy
    0.10
    ä¸Ģ声
    0.10
    ä¸ĬæĿ¥
    0.10
    çĴ©
    0.10
    ä¸į论æĺ¯
    0.10
     atenção
    0.10
     Attention
    0.09
    Activations Density 0.106%

    No Known Activations