© 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. 61413
    Prev
    Next
    INDEX
    Explanations

    Baker Prize and company names

    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
    ful
    -0.09
    èĥ±
    -0.09
    nable
    -0.09
    alen
    -0.08
    é¦Ļæ°´
    -0.08
     ÑģебÑı
    -0.08
    ök
    -0.08
    cript
    -0.08
    _SAMPL
    -0.08
    pes
    -0.08
    POSITIVE LOGITS
    intosh
    0.10
     вÑģего
    0.10
    æ²¥
    0.10
    æĻļé¥Ń
    0.09
    ç°Į
    0.09
    апÑĢ
    0.09
    èĻIJ
    0.09
    æł·çļĦ
    0.09
    esson
    0.09
    ÑĢон
    0.09
    Activations Density 0.009%

    No Known Activations