© 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. 871
    Prev
    Next
    INDEX
    Explanations

    quantities and measures

    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
    æĿ·
    -0.09
    åĽºåĮĸ
    -0.09
    篷
    -0.09
    èĸª
    -0.09
    形象
    -0.09
    çļĦ形象
    -0.09
    èī¯æĢ§
    -0.08
    éĿ©
    -0.08
    象
    -0.08
    ä¸Ģç±»
    -0.08
    POSITIVE LOGITS
    容åĻ¨
    0.12
    缼
    0.10
     container
    0.10
    ëŁī
    0.10
     containers
    0.10
    ãĤµãĤ¤ãĤº
    0.10
    åĪĽå§ĭ
    0.09
     Containers
    0.09
    è¿·ä½ł
    0.09
    Containers
    0.09
    Activations Density 0.069%

    No Known Activations