© 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. 55511
    Prev
    Next
    INDEX
    Explanations

    by playingfrom serverfrom setby looking

    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
    anky
    -0.09
    è³ŀ
    -0.09
    æĺİç¡®æıIJåĩº
    -0.08
     chron
    -0.08
    arked
    -0.08
    nder
    -0.08
    èµı
    -0.08
    ä¹Łå¥½
    -0.08
    ä¸Ģä¼ļ
    -0.08
    chron
    -0.08
    POSITIVE LOGITS
    itsu
    0.11
    çľĭåĩº
    0.10
    mere
    0.10
    çľĭäºĨ
    0.10
    ä¸Ģçľĭ
    0.09
    èĽĽ
    0.09
    FromBody
    0.09
    å¤ĸ表
    0.09
    å¯Ł
    0.09
    è²Į
    0.09
    Activations Density 0.124%

    No Known Activations