© 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. 38666
    Prev
    Next
    INDEX
    Explanations

    subject matter disclosed

    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
    çļĦæ¨¡æł·
    -0.09
    æªĢ
    -0.09
    oire
    -0.09
    ÙĨÙĤ
    -0.09
    ä¸Ģéģĵ
    -0.08
    åĪĬ
    -0.08
    Ø´
    -0.08
    æŀģ
    -0.08
    sounds
    -0.08
    UBLE
    -0.08
    POSITIVE LOGITS
    é¢ĨåŁŁçļĦ
    0.11
    éĥ¨åī¯
    0.10
    éĥ¨éĥ¨éķ¿
    0.10
    éĥ¨åī¯éĥ¨éķ¿
    0.10
    åĴĮæĬĢæľ¯
    0.10
    arpa
    0.10
    é¢ĨåŁŁ
    0.09
    æij
    0.09
    第ä¸Ģéĥ¨
    0.09
    ifest
    0.09
    Activations Density 0.021%

    No Known Activations