© 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. 34102
    Prev
    Next
    INDEX
    Explanations

    functionality

    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
    æł·çļĦ
    -0.10
    ç»
    -0.10
    ãģĹãģ¾ãģĦ
    -0.10
    esting
    -0.10
    ee
    -0.09
    éļ¾åħ³
    -0.09
    able
    -0.09
    inger
    -0.09
    ings
    -0.09
    peed
    -0.09
    POSITIVE LOGITS
    å°ıé¢Ŀ
    0.09
    áĢĿ
    0.09
    ä¸įæĸŃå®ĮåĸĦ
    0.09
    zar
    0.09
    ities
    0.09
    tes
    0.09
    Çİ
    0.08
    ties
    0.08
    keiten
    0.08
    ÑĤÑı
    0.08
    Activations Density 0.034%

    No Known Activations