© 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. 30262
    Prev
    Next
    INDEX
    Explanations

    for that reason

    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
    俱
    -0.10
    inality
    -0.10
    _SIG
    -0.09
    elas
    -0.09
    mdb
    -0.09
    ä¸įåIJĮç¨ĭ度
    -0.09
    èĴ¸æ±½
    -0.09
    uien
    -0.09
    truth
    -0.09
    outu
    -0.09
    POSITIVE LOGITS
    en
    0.09
    enco
    0.08
    bject
    0.08
    æŀ¯çĩ¥
    0.08
    çļĦåħ³æ³¨
    0.08
    æģ©
    0.08
    导åIJij
    0.08
    åİĭåĪ¶
    0.08
    ÑĢÑĥÑĩ
    0.08
    åıijå±ķ模å¼ı
    0.08
    Activations Density 0.002%

    No Known Activations