© 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. 26057
    Prev
    Next
    INDEX
    Explanations

    achieving a goal

    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
    楷
    -0.10
    éĴī
    -0.09
    æĢª
    -0.08
    æĻĴ
    -0.08
    èµ·ä¼ı
    -0.08
    åıijæĺİ
    -0.08
    VENT
    -0.08
    模èĮĥ
    -0.08
    éĢļå¾Ģ
    -0.08
    esh
    -0.08
    POSITIVE LOGITS
    é¡¿æŶ
    0.10
    åħĶ
    0.10
    æĪij们è¦ģ
    0.10
    .defaults
    0.09
    ä¸ĢæĬ¹
    0.09
    imson
    0.09
    ç»Ŀ
    0.09
    eled
    0.09
    æīĵçł´
    0.09
     немного
    0.09
    Activations Density 0.015%

    No Known Activations