© 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. 31620
    Prev
    Next
    INDEX
    Explanations

    navigation links and app features

    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
    è§ģè¯Ĩ
    -0.09
    æĽ²
    -0.09
    èĵĿ天
    -0.09
     ca
    -0.09
    æ´Ļ
    -0.09
    è§ģ
    -0.09
    åŀĵ
    -0.09
    cek
    -0.09
    rames
    -0.08
    èĤ¡æ°ij
    -0.08
    POSITIVE LOGITS
    _IMPLEMENT
    0.09
    å¾Ĵ
    0.09
    .Strict
    0.08
    æĢ¥éľĢ
    0.08
    ç½ķ
    0.08
    éĥģ
    0.08
    enheim
    0.08
    ÑİÑĢ
    0.08
    .codehaus
    0.08
    PIP
    0.08
    Activations Density 0.118%

    No Known Activations