© 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. 755
    Prev
    Next
    INDEX
    Explanations

    subject or matter

    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¿Ļç§įæĸ¹å¼ı
    -0.11
    _ISO
    -0.10
    æĬĬè¿ĻäºĽ
    -0.09
    è¿Ļæł·åģļ
    -0.09
    å¾Ģä¸Ĭ
    -0.09
    ly
    -0.09
    ä¼
    -0.09
    è¿Ļç§įæĸ¹æ³ķ
    -0.08
    éĤ£ä»½
    -0.08
    ãģ¶ãĤĬ
    -0.08
    POSITIVE LOGITS
     matter
    0.11
    èģĶ
    0.09
     Vend
    0.08
    /query
    0.08
     Matter
    0.08
    via
    0.08
    opa
    0.08
    avid
    0.08
    èĪ«
    0.08
    æ°©
    0.08
    Activations Density 0.081%

    No Known Activations