© 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. 22992
    Prev
    Next
    INDEX
    Explanations

    enzyme immunoassay

    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
    aven
    -0.10
    į
    -0.10
    lington
    -0.09
    ner
    -0.08
    ction
    -0.08
    iable
    -0.08
     Joh
    -0.08
    ney
    -0.08
    ne
    -0.08
    langs
    -0.08
    POSITIVE LOGITS
    ically
    0.09
    uet
    0.09
    ÙĪع
    0.09
    æīijåħĭ
    0.09
    infinity
    0.09
    Ñģки
    0.09
    кÑĢа
    0.08
    akra
    0.08
    èij«èĬ¦
    0.08
     sudoku
    0.08
    Activations Density 0.121%

    No Known Activations