© 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. 903
    Prev
    Next
    INDEX
    Explanations

    independence and autonomy

    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
    Not in Any Lists

    No Comments

    Negative Logits
    好äºĭ
    -0.09
    æ§
    -0.09
    éķľ
    -0.08
    çĥĤ
    -0.08
    ç¡IJ
    -0.08
    ç³Ł
    -0.08
    èµŀæĪIJ
    -0.08
    çĵ·
    -0.08
     Hess
    -0.08
    éģĹ
    -0.08
    POSITIVE LOGITS
    çĭ¬ç«ĭ
    0.41
    çį¨ç«ĭ
    0.36
     independence
    0.35
     Independence
    0.29
     independ
    0.28
    Independ
    0.28
     independent
    0.27
    èĩªä¸»
    0.25
    Independent
    0.25
     ÑģамоÑģÑĤоÑı
    0.25
    Activations Density 0.086%

    No Known Activations