© 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. 57426
    Prev
    Next
    INDEX
    Explanations

    negation or no

    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
    æĵĺ
    -0.10
    ç³Ł
    -0.10
    enas
    -0.10
    éļıæīĭ
    -0.10
    argon
    -0.09
    ç³ķ
    -0.09
    _argument
    -0.09
    èĪĤ
    -0.09
    åŃIJå¼Ł
    -0.09
    æĻ´
    -0.09
    POSITIVE LOGITS
    ä¸Ŀ毫
    0.11
    æľīä»»ä½ķ
    0.11
    å°ĨæĿ¥
    0.10
    ä¸įåĪ©
    0.09
     Fame
    0.09
    å°ı康社ä¼ļ
    0.09
    usc
    0.09
    èĩ³äºİ
    0.09
    ä¼łéĹ»
    0.09
    æĭĵ宽
    0.09
    Activations Density 0.066%

    No Known Activations