© 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. 32320
    Prev
    Next
    INDEX
    Explanations

    contagious infection spread

    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
    èĿ®
    -0.09
    usta
    -0.09
    çģ«çģ¾
    -0.09
    伤亡
    -0.09
     Quarter
    -0.09
    æľīå¿ħè¦ģ
    -0.09
    kus
    -0.09
    éªĬ
    -0.08
    æĺ¯å¯¹
    -0.08
    æĬ
    -0.08
    POSITIVE LOGITS
    å¯ĨéĽĨ
    0.10
    ä¼łæĴŃ
    0.09
    åķ¬
    0.09
    æ³®
    0.09
    åħįç¨İ
    0.08
    夷
    0.08
    å®£ä¼łæķĻèĤ²
    0.08
    è°ħ解
    0.08
    çIJİ
    0.08
    بØŃ
    0.08
    Activations Density 0.040%

    No Known Activations