© 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. 40181
    Prev
    Next
    INDEX
    Explanations

    this kind of

    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
    ä¸Ģäºĭ
    -0.09
    asil
    -0.09
    è·Łå¥¹
    -0.09
    ãĥ¢ãĥİ
    -0.09
    _closure
    -0.09
    ä¸ĵ访
    -0.08
    TestFixture
    -0.08
     shred
    -0.08
    .Annotations
    -0.08
     Alf
    -0.08
    POSITIVE LOGITS
    è¿Ļç±»
    0.10
    æѤ类
    0.09
    еÑĩен
    0.09
    è¿Ļ款
    0.09
    诸å¦Ĥ
    0.09
    çĽ²
    0.09
    åķ¬
    0.08
    ä¸į满
    0.08
    éĤ£äºĽ
    0.08
    éĶĻè¿ĩ
    0.08
    Activations Density 1.538%

    No Known Activations