© 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. 29410
    Prev
    Next
    INDEX
    Explanations

    naming conventions

    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
    _eff
    -0.09
    å½ķåħ¥
    -0.09
    åĬª
    -0.09
    çªij
    -0.09
    illon
    -0.09
    ç»ı
    -0.08
    oster
    -0.08
    çŃĶåį·
    -0.08
     Kling
    -0.08
    EMS
    -0.08
    POSITIVE LOGITS
    åIJ¬èµ·æĿ¥
    0.09
    åĨįçĶŁ
    0.09
    éħ¿
    0.09
    اظ
    0.09
    诸å¦Ĥ
    0.09
    éĨī
    0.08
    éħĿ
    0.08
    ä¸įæ¸ħ
    0.08
    gebung
    0.08
    æĻ¦
    0.08
    Activations Density 0.078%

    No Known Activations