© 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. 18671
    Prev
    Next
    INDEX
    Explanations

    3 point loss

    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
     Boxing
    -0.09
    æĭ³
    -0.09
    æ¸ħéĨĴ
    -0.08
    cheon
    -0.08
    UNE
    -0.08
    PGA
    -0.08
    POSE
    -0.08
    å¾·å·ŀ
    -0.08
     thẩm
    -0.08
    iku
    -0.08
    POSITIVE LOGITS
    ç»Ħ建
    0.09
    沪
    0.09
     sach
    0.09
    趴
    0.09
    _reserve
    0.09
    æŃĨ
    0.09
    æĪĺ
    0.09
    é¦ĸè½®
    0.09
    èIJ¸
    0.09
    ç½IJ
    0.08
    Activations Density 0.072%

    No Known Activations