© 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. 2864
    Prev
    Next
    INDEX
    Explanations

    crypt followed by words like analytic, ome, soft, os, omon

    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
    manship
    -0.09
    uration
    -0.09
    ething
    -0.09
    LAG
    -0.08
    \uD
    -0.08
    æĸ¥
    -0.08
    pects
    -0.08
    rud
    -0.08
    æģIJæħĮ
    -0.08
    iper
    -0.08
    POSITIVE LOGITS
    omic
    0.10
    ically
    0.09
    ÑĨев
    0.09
    nic
    0.09
    sterol
    0.09
    vir
    0.09
    ological
    0.09
    обоÑĢ
    0.09
    antis
    0.09
    ocurrency
    0.08
    Activations Density 0.024%

    No Known Activations