© 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. 48052
    Prev
    Next
    INDEX
    Explanations

    real estate and financial transactions

    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
    ä¸įæŃ»
    -0.12
    velle
    -0.10
     nightly
    -0.09
    hiro
    -0.09
    沸
    -0.09
    -hole
    -0.09
    æİ¥æīĭ
    -0.09
    eres
    -0.09
    亲人
    -0.08
    lier
    -0.08
    POSITIVE LOGITS
    åīįæīĢ
    0.09
    è°İ
    0.09
    积èĵĦ
    0.08
    enÃŃ
    0.08
    é¦ĸ
    0.08
    ç«ĭãģ¡
    0.08
    ноп
    0.08
    ÙĪÙĨÙĬ
    0.08
    pedia
    0.08
    miss
    0.08
    Activations Density 0.007%

    No Known Activations