© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 40197
    Prev
    Next
    INDEX
    Explanations

    injury and damage

    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
    Negative Logits
    è§ģéĿ¢
    -0.09
    è´ŀ
    -0.09
    umer
    -0.09
    å¢ŀè¿Ľ
    -0.09
    azing
    -0.09
    é«ĺåİŁ
    -0.09
    sie
    -0.09
    å¾Ģä¸ĭ
    -0.09
    PEAR
    -0.09
    赡
    -0.08
    POSITIVE LOGITS
    çŃĭ
    0.09
    (InputStream
    0.08
     pil
    0.08
    æµģæ°ĵ
    0.08
    çѵ
    0.08
    êµ°
    0.08
    çļĦ好
    0.08
    ung
    0.08
    eps
    0.08
    undra
    0.07
    Activations Density 0.010%

    No Known Activations