© 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. 34617
    Prev
    Next
    INDEX
    Explanations

    expressing negative outcomes or satisfaction

    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
    oded
    -0.09
    æĹłçĸijæĺ¯
    -0.09
    azor
    -0.09
    èĬ¥
    -0.08
    éªĬ
    -0.08
    ãĤĭãģ¨
    -0.08
    åĿ·
    -0.08
    红åĪ©
    -0.08
    èµ·ä¾Ĩ
    -0.08
    å°´å°¬
    -0.08
    POSITIVE LOGITS
    æĺ¯åľ¨
    0.10
    cket
    0.09
    /help
    0.09
    æľī个
    0.09
    éŀĺ
    0.09
    utsche
    0.09
     slick
    0.08
    yan
    0.08
    家åĸ»æĪ·æĻĵ
    0.08
    åĪ¶æľį
    0.08
    Activations Density 0.001%

    No Known Activations