© 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. 56661
    Prev
    Next
    INDEX
    Explanations

    uses cookies

    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
    èĨ¨
    -0.10
    éĨħ
    -0.10
    jem
    -0.09
    åĿĢ
    -0.09
    å·¥åķĨå±Ģ
    -0.09
    åĨĻçĿĢ
    -0.09
    unch
    -0.09
    åIJĦèĩªçļĦ
    -0.09
    åĴĤ
    -0.09
    _OW
    -0.09
    POSITIVE LOGITS
     Indo
    0.09
    便
    0.08
     PARTICULAR
    0.08
    ä¸įå±ŀäºİ
    0.08
    itta
    0.08
     CLOSED
    0.08
    ä¸įåĨį
    0.08
     lean
    0.07
     ÑįнеÑĢги
    0.07
    ären
    0.07
    Activations Density 0.088%

    No Known Activations