© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52827
    Prev
    Next
    INDEX
    Explanations

    referring to parents

    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
    obb
    -0.10
    uien
    -0.09
     cứ
    -0.09
    ฯ
    -0.09
     sexes
    -0.09
    è¡·å¿ĥ
    -0.09
    ä½İ温
    -0.08
    æĭŃ
    -0.08
    osci
    -0.08
    strap
    -0.08
    POSITIVE LOGITS
    éļIJçŀĴ
    0.09
    姣
    0.08
    涨
    0.08
    rsp
    0.08
    trail
    0.08
    æļ´åĬĽ
    0.08
    resultSet
    0.08
    éĢ£ãĤĮ
    0.08
    ãĤĮ
    0.07
    fat
    0.07
    Activations Density 0.009%

    No Known Activations