© 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. 33170
    Prev
    Next
    INDEX
    Explanations

    court or Court

    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
    inters
    -0.09
    为äºĨæĽ´å¥½
    -0.08
    ãĥ³ãĤ°
    -0.08
     nonatomic
    -0.08
    足迹
    -0.07
    etter
    -0.07
    loit
    -0.07
    åħ¥å¢ĥ
    -0.07
    稿
    -0.07
    çĿ£åĬŀ
    -0.07
    POSITIVE LOGITS
    ney
    0.13
    ç¿
    0.10
    à¤Ľ
    0.10
    fully
    0.10
    laÅŁ
    0.10
    åĵĩ
    0.09
    失æķĪ
    0.09
    èIJ¥
    0.09
    lg
    0.09
    eenth
    0.09
    Activations Density 0.018%

    No Known Activations