© 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. 64136
    Prev
    Next
    INDEX
    Explanations

    search or looking for

    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
    trail
    -0.09
     cannon
    -0.09
     Cannon
    -0.08
    åģ·åģ·
    -0.08
    æĺ¨å¤©
    -0.08
    èĤ©
    -0.08
    å¤įå·¥
    -0.08
    康
    -0.08
    æĬĢ
    -0.08
     visita
    -0.08
    POSITIVE LOGITS
    寻æī¾
    0.24
    寻
    0.23
    å°ĭ
    0.18
    æIJľç´¢
    0.17
    è§ħ
    0.17
    æī¾äºĨ
    0.16
     search
    0.16
    æī¾å·¥ä½ľ
    0.16
     поиÑģк
    0.15
     searching
    0.15
    Activations Density 0.088%

    No Known Activations