© 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. 56277
    Prev
    Next
    INDEX
    Explanations

    such as in descriptions

    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
    äºĨä¸įå°ij
    -0.11
    lew
    -0.09
    èĥ¸åīį
    -0.09
    äºĨ好
    -0.09
    GIN
    -0.09
     Glad
    -0.09
    æľīä¸įå°ij
    -0.09
    /release
    -0.09
    èİī
    -0.08
    gin
    -0.08
    POSITIVE LOGITS
    php
    0.09
    æŶæŶ
    0.09
    à¸ĸà¸Ļ
    0.08
    adan
    0.08
    ä¼ĺ
    0.08
    hum
    0.08
    æīįæĺ¯çľŁæŃ£
    0.08
     же
    0.08
    庶
    0.08
    æĿĥå¨ģ
    0.08
    Activations Density 0.056%

    No Known Activations