© 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. 17688
    Prev
    Next
    INDEX
    Explanations

    negation of outcome

    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
    anga
    -0.10
    åľ¨è¿Ļç§į
    -0.10
    åľ¨åĵªéĩĮ
    -0.10
    寡
    -0.09
    æIJľéĽĨ
    -0.09
    æľīå¾Īå¤ļ
    -0.09
    æľīä¸įå°ij
    -0.08
    å¹¼
    -0.08
     UPLOAD
    -0.08
     whichever
    -0.08
    POSITIVE LOGITS
     regard
    0.14
     regards
    0.12
    åīįéĢĶ
    0.11
    迹象
    0.09
    chy
    0.09
    æĤ¬å¿µ
    0.09
    hone
    0.08
     chance
    0.08
    ç¾ŀ
    0.08
    undi
    0.08
    Activations Density 0.019%

    No Known Activations