© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35538
    Prev
    Next
    INDEX
    Explanations

    saint places

    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
    微信åı·
    -0.09
    ä»»èģĮ
    -0.08
    ä¸ĵ项è¡ĮåĬ¨
    -0.08
    icamente
    -0.08
    nda
    -0.07
    ore
    -0.07
    ä½
    -0.07
    æĸ¯å¡Ķ
    -0.07
    ingly
    -0.07
     Türk
    -0.07
    POSITIVE LOGITS
    tester
    0.10
    .sd
    0.09
    quia
    0.09
    pent
    0.09
    ÃŃda
    0.09
     Cyril
    0.09
    thing
    0.08
    vidence
    0.08
    raphics
    0.08
    roller
    0.08
    Activations Density 0.020%

    No Known Activations