© 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. 54606
    Prev
    Next
    INDEX
    Explanations

    of [X] noun phrases

    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
    /of
    -0.09
    äºĭåĦ¿
    -0.09
    çļĦåĬªåĬĽ
    -0.09
    æĺ¯æĪij们
    -0.08
    sandbox
    -0.08
    веÑĩ
    -0.08
    转åŀĭ
    -0.08
    çļĦåľ°æŃ¥
    -0.08
    çļĦ表æĥħ
    -0.08
    обÑī
    -0.08
    POSITIVE LOGITS
    åIJĪéĢĤ
    0.09
    大éĩı
    0.09
    åIJĪéĢĤçļĦ
    0.08
    /up
    0.08
    an
    0.08
    à¸ŀา
    0.08
     genuinely
    0.08
     both
    0.08
    æŁIJç§į
    0.08
    æĸ°çļĦ
    0.08
    Activations Density 0.302%

    No Known Activations