© 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. 58932
    Prev
    Next
    INDEX
    Explanations

    CAD and design software

    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
    é¢ł
    -0.10
    è¿Ĥ
    -0.08
    微微
    -0.08
     Covered
    -0.08
    ç¼ĺ
    -0.08
     микÑĢо
    -0.08
    ç«Ļéķ¿
    -0.07
    å°ıåѦ
    -0.07
    ç¤ģ
    -0.07
     sod
    -0.07
    POSITIVE LOGITS
    èıŁ
    0.11
    ä½ıåľ¨
    0.10
    鼶件
    0.10
    ounsel
    0.10
    دÙĨÙĬ
    0.10
    .metamodel
    0.10
    bish
    0.09
    å®ŀçī©
    0.09
     FOX
    0.09
     henne
    0.09
    Activations Density 0.127%

    No Known Activations