© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 37185
    Prev
    Next
    INDEX
    Explanations

    stored procedure

    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
    çļĦåΰæĿ¥
    -0.09
    зи
    -0.09
    åIJįèªī
    -0.09
    ä¹ĭæĥħ
    -0.08
    éĶŃ
    -0.08
    GuidId
    -0.08
    cassert
    -0.08
    _REC
    -0.08
    oot
    -0.08
    ÄĻ
    -0.08
    POSITIVE LOGITS
     disreg
    0.09
    istan
    0.09
    IME
    0.09
    auf
    0.08
     cst
    0.08
    çļĸ
    0.08
    /private
    0.08
    åıĬ以ä¸Ĭ
    0.08
    åıijå±ķä¸Ń
    0.08
    plat
    0.08
    Activations Density 1.658%

    No Known Activations