© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7103
    Prev
    Next
    INDEX
    Explanations

    punctuation and questions

    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
    wiki
    -0.10
    èĤ¡æľ¬
    -0.09
    åħ¨åªĴä½ĵ
    -0.09
    诺è´Ŀå°Ķ
    -0.08
    举
    -0.08
    å²±
    -0.08
    ä¿Ĺè¯Ŀ说
    -0.08
    able
    -0.08
    _refl
    -0.08
    straints
    -0.08
    POSITIVE LOGITS
    çŃīçŃī
    0.10
    ators
    0.09
    绣绣
    0.09
    isen
    0.09
    çŃīå½¢å¼ı
    0.09
    _STRIP
    0.09
    æľºä¼ļ
    0.08
     etc
    0.08
    oppers
    0.08
    ç«Łæĺ¯
    0.08
    Activations Density 0.103%

    No Known Activations