© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 60638
    Prev
    Next
    INDEX
    Explanations

    connectivity and prefixes

    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
    Negative Logits
    hood
    -0.10
    常å§Ķä¼ļ
    -0.10
    éªĦ
    -0.10
    ä¸ĵ人
    -0.10
    qli
    -0.09
    _PKT
    -0.09
    лиÑĨ
    -0.09
    -0.09
    ĭ
    -0.09
    DBObject
    -0.09
    POSITIVE LOGITS
    icut
    0.10
    exion
    0.10
    olly
    0.09
    æŁıæŀĹ
    0.09
    èĩ¾
    0.08
    éļ³
    0.08
    ihat
    0.08
    è±ķ
    0.08
    IVITY
    0.08
    ibur
    0.08
    Activations Density 0.034%

    No Known Activations