© 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. 54061
    Prev
    Next
    INDEX
    Explanations

    Coca-Cola, codecs, cochlea

    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
    OfWork
    -0.11
    iales
    -0.10
    èħ¹
    -0.08
    à¸Ĥา
    -0.08
    éļĶ
    -0.08
    anger
    -0.08
    ви
    -0.08
    ial
    -0.08
    ioni
    -0.08
    à¸Ľà¸¥à¸²à¸¢
    -0.08
    POSITIVE LOGITS
    çĦ¶æĺ¯
    0.10
    eras
    0.10
    æŸ
    0.10
    teenth
    0.10
    ivity
    0.09
    æ¦Ķ
    0.09
    é¹Ń
    0.09
    bine
    0.09
    culate
    0.09
    å±Ĥåĩº
    0.08
    Activations Density 0.014%

    No Known Activations