© 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. 48892
    Prev
    Next
    INDEX
    Explanations

    a followed by adjective or noun

    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
     Andreas
    -0.09
    æ´¥
    -0.09
    ssf
    -0.09
    èŀŁ
    -0.09
    æĹĸ
    -0.09
    临
    -0.09
    æĺŁè¾°
    -0.09
    è³¢
    -0.08
    æľĽçĿĢ
    -0.08
    ort
    -0.08
    POSITIVE LOGITS
    _nd
    0.09
    eh
    0.09
    å·¦æīĭ
    0.09
    ODO
    0.09
    subscribe
    0.08
    åĴĮ社ä¼ļ
    0.08
    ä¸Ģå°ģ
    0.08
    è§ĦèĮĥ
    0.08
    çIJĨæĥ³
    0.08
    esen
    0.08
    Activations Density 0.075%

    No Known Activations