© 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. 24144
    Prev
    Next
    INDEX
    Explanations

    on top 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
    èĥĦ
    -0.10
    iem
    -0.09
    å½ĵä»ĸ
    -0.09
    ä¸Ĭå®ĺ
    -0.09
    aub
    -0.09
    éĿ
    -0.09
    à¤ł
    -0.09
    æĻ´
    -0.08
    .struct
    -0.08
    è±ļ
    -0.08
    POSITIVE LOGITS
    æĪijåıijçİ°
    0.09
    datable
    0.09
    åĦ¿
    0.08
    åı¯ä»¥éĢīæĭ©
    0.08
    ya
    0.08
     Ñģобой
    0.08
    éĤ£äºĽ
    0.08
    ÑĢÑĥж
    0.08
    åİŁæľīçļĦ
    0.08
    åѦåĪ°
    0.08
    Activations Density 0.009%

    No Known Activations