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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36668
    Prev
    Next
    INDEX
    Explanations

    operating system installation

    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
    ä¸įåIJĪçIJĨ
    -0.09
     bãi
    -0.08
    plib
    -0.08
    ASA
    -0.08
    èµĿ
    -0.08
    sem
    -0.08
    Slf
    -0.08
    çĽij管éĥ¨éŨ
    -0.08
    _mtime
    -0.08
    å¢ŀæĮģ
    -0.08
    POSITIVE LOGITS
    庶
    0.10
    裸
    0.10
    åºĦ严
    0.09
    çħĮ
    0.09
    aze
    0.09
    é»ij马
    0.08
    ä¸Ģå¼ł
    0.08
    ÑĥÑīе
    0.08
    çĽĺ
    0.08
    .exc
    0.08
    Activations Density 0.144%

    No Known Activations