© 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. 3849
    Prev
    Next
    INDEX
    Explanations

    his or her

    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
    ä¸įäºĨ
    -0.10
    _FWD
    -0.09
    ledge
    -0.09
    鸳
    -0.09
     notch
    -0.09
    讲è¯Ŀ
    -0.09
    éĥ½è¯´
    -0.08
    ãģĦãģĨ
    -0.08
    æĻºéĢł
    -0.08
    ç²ij
    -0.08
    POSITIVE LOGITS
    /her
    0.15
    /she
    0.11
     or
    0.10
    æĪĸ
    0.09
    她们
    0.08
     veya
    0.08
    姹
    0.08
    临港
    0.08
    (s
    0.07
    åIJĦèĩª
    0.07
    Activations Density 0.089%

    No Known Activations