© 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. 39135
    Prev
    Next
    INDEX
    Explanations

    athletic events and actions

    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
    æ²ĥå°Ķ
    -0.09
    ç²īç¢İ
    -0.08
    aille
    -0.08
    åıijèĤ²
    -0.08
    åĴı
    -0.08
    ãĤģãģ¦
    -0.08
    åĩºä¼Ĺ
    -0.08
    åĨ³å®ļ
    -0.08
    对éĿ¢
    -0.07
    åĬŁè¯¾
    -0.07
    POSITIVE LOGITS
    ãĤ¹ãĤŃ
    0.10
    å¼Ī
    0.10
    ede
    0.09
    é£
    0.09
    æ¼ı
    0.09
    +xml
    0.09
    åij£
    0.08
    lesc
    0.08
    Unmarshaller
    0.08
    ä¸Ńç§ĭ
    0.08
    Activations Density 0.002%

    No Known Activations