© 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. 49212
    Prev
    Next
    INDEX
    Explanations

    fields and areas of

    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
    åĪ«è¯´
    -0.09
    人们çļĦ
    -0.09
    ä¹IJè§Ĥ
    -0.09
    èĥ´
    -0.09
    orn
    -0.08
    对åħ¶è¿Ľè¡Į
    -0.08
    åĪ«äººçļĦ
    -0.08
    éĻ©
    -0.08
    çĶŁäº§èĥ½åĬĽ
    -0.08
     ÑĥÑģили
    -0.08
    POSITIVE LOGITS
    orque
    0.09
    Americ
    0.09
    ès
    0.09
    æĭŁå®ļ
    0.09
    \Twig
    0.09
    åŁŁ
    0.09
    éĶĴ
    0.08
    eltas
    0.08
    )index
    0.08
    'field
    0.08
    Activations Density 0.050%

    No Known Activations