© 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. 63071
    Prev
    Next
    INDEX
    Explanations

    field of the invention or section

    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
    èµ
    -0.08
    çĻŀ
    -0.08
    å¼ŁåħĦ
    -0.08
    å¤ļåľ°
    -0.08
    BU
    -0.08
    sock
    -0.08
     oe
    -0.08
    çľĭä»ĸ
    -0.08
    è·¨çķĮ
    -0.08
     Sonata
    -0.08
    POSITIVE LOGITS
    æĬ¥åijĬæľŁåĨħ
    0.09
    ä¸Ńå°ıä¼ģä¸ļ
    0.09
    omb
    0.09
    æĹłç¼Ŀ
    0.09
    Stored
    0.08
    AsyncResult
    0.08
     Vulcan
    0.08
    _any
    0.08
     repost
    0.08
    yu
    0.08
    Activations Density 0.054%

    No Known Activations