© 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. 54276
    Prev
    Next
    INDEX
    Explanations

    embarrassment or embarrassing

    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
    дол
    -0.11
    æŃ¥æŃ¥
    -0.09
    ä¸įåħį
    -0.09
    igraphy
    -0.09
    èѦæĥķ
    -0.09
    ç²¹
    -0.08
    ization
    -0.08
    ìį¨
    -0.08
    BACK
    -0.08
     Dane
    -0.08
    POSITIVE LOGITS
    ingly
    0.10
    å¾Ĵå¼Ł
    0.10
    ilet
    0.10
    edia
    0.09
    ments
    0.09
    åIJİèĢħ
    0.09
    .setAction
    0.09
    ecute
    0.09
    åĭĥåĭĥ
    0.08
     spokes
    0.08
    Activations Density 0.002%

    No Known Activations