© 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. 17271
    Prev
    Next
    INDEX
    Explanations

    courts

    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
    ç¥ĸåĽ½
    -0.10
    å½ķéŁ³
    -0.09
    ble
    -0.09
    _scan
    -0.09
    å½ķ
    -0.08
     Scan
    -0.08
    اÙħØ©
    -0.08
    æī«æıı
    -0.08
    ãģĴ
    -0.08
    ##_
    -0.08
    POSITIVE LOGITS
    æ¥Ķ
    0.10
    解åĨ³éĹ®é¢ĺ
    0.10
    èµĮ
    0.09
    主åĬ¨æĢ§
    0.09
    ä¿Ŀ驾
    0.09
    etus
    0.09
    åıĹçIJĨ
    0.09
    lbrace
    0.09
    _ABI
    0.08
    çļĦæĪĺçķ¥
    0.08
    Activations Density 0.139%

    No Known Activations