© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 49417
    Prev
    Next
    INDEX
    Explanations

    colonial settlements and founders

    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
    æĤį
    -0.09
    çīºçī²
    -0.08
    解æĶ¾åĨĽ
    -0.08
    åı¤ä»Ĭ
    -0.08
    çļĦåİĨåı²
    -0.08
    ëŀĮ
    -0.08
    loader
    -0.08
    èĿĻ
    -0.08
    oin
    -0.08
    éķĤ
    -0.08
    POSITIVE LOGITS
    .getPort
    0.09
    å¼ķãģį
    0.09
    æĺ¥å¤©
    0.09
    аÑĢи
    0.09
    磶
    0.08
    åħįç¨İ
    0.08
    æĺ¥åŃ£
    0.08
    ä¸ī个æľĪ
    0.08
    èĪ±
    0.08
    西äºļ
    0.08
    Activations Density 0.112%

    No Known Activations