© 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. 59373
    Prev
    Next
    INDEX
    Explanations

    names starting with K

    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
    å¥ī
    -0.09
    è¶Ĭ
    -0.09
    маÑĢ
    -0.09
    Ä°LÄ°
    -0.09
    ç§ģä¸ĭ
    -0.08
     frau
    -0.08
    çĴĭ
    -0.08
    ä¸Ģ次æĢ§
    -0.08
    üyü
    -0.08
    apon
    -0.08
    POSITIVE LOGITS
    çļ±çº¹
    0.10
    .isRequired
    0.09
    åĨ
    0.08
    éĽķ
    0.08
    ÑĮе
    0.08
    æ²¥
    0.08
    iero
    0.08
    æĶ¶æķĽ
    0.08
    raised
    0.08
    çĶ¨å¾®ä¿¡
    0.08
    Activations Density 0.040%

    No Known Activations