© 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. 62960
    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
    æĮĩæķ°
    -0.09
    åħįç¨İ
    -0.09
    æĿµ
    -0.08
    æ·±åħ¥äºĨ解
    -0.08
     пÑĢеп
    -0.08
     Pill
    -0.08
     ứng
    -0.08
    åİ®
    -0.08
    åį¯
    -0.08
    зв
    -0.08
    POSITIVE LOGITS
    äºĶæĺŁ
    0.11
    decorators
    0.09
    .decorate
    0.09
    æĸĭ
    0.09
    ç¯ĩ
    0.09
    ÑĢенд
    0.08
    åĪĩæĸŃ
    0.08
    ckt
    0.08
    Ton
    0.08
    otland
    0.08
    Activations Density 0.031%

    No Known Activations