© 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. 18723
    Prev
    Next
    INDEX
    Explanations

    court of appeals

    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
    endra
    -0.10
    寸
    -0.10
    åĴĮå¹³
    -0.09
    æĹłæĥħ
    -0.09
    instr
    -0.09
     bá»ı
    -0.09
    senal
    -0.09
    ัà¸į
    -0.08
    éĦĦ
    -0.08
    printStats
    -0.08
    POSITIVE LOGITS
    æł·çļĦ
    0.11
    累累
    0.10
    ever
    0.09
    soever
    0.09
    輩
    0.09
    uff
    0.08
    åģ»
    0.08
    以åıĬåħ¶ä»ĸ
    0.08
    å°±å¾Ĺ
    0.08
    ä¾ij
    0.08
    Activations Density 0.060%

    No Known Activations