© 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. 57985
    Prev
    Next
    INDEX
    Explanations

    argument ending in bullshit

    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
    è·Ĺ
    -0.10
    好åĥıæĺ¯
    -0.09
    æĪij说
    -0.09
    åij
    -0.09
    ä¸İä¼Ĺä¸įåIJĮ
    -0.09
    æijĩäºĨ
    -0.09
    éĴ¿
    -0.09
    CTS
    -0.09
     seemingly
    -0.09
    èµ³
    -0.08
    POSITIVE LOGITS
    ä»»ä½ķ人
    0.09
     Hall
    0.09
    åĨįåĪ°
    0.09
    .yang
    0.08
    å°±åľ¨äºİ
    0.08
    inh
    0.08
    é©¿ç«Ļ
    0.08
    .ant
    0.08
    ä»»ä½ķ
    0.08
    è¾ľè´Ł
    0.08
    Activations Density 0.072%

    No Known Activations