© 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. 48467
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units

    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
    è¾ĩ
    -0.11
    ç»ıéªĮåĴĮ
    -0.10
    è¿Ļ项
    -0.10
    amu
    -0.10
    管çIJĨåĴĮ
    -0.10
    为æĤ¨æıIJä¾Ľ
    -0.09
    .Must
    -0.09
    راÙħ
    -0.09
    å®ĮäºĨ
    -0.09
    ä¼ģä¸ļåĴĮ
    -0.09
    POSITIVE LOGITS
     dozen
    0.11
    rap
    0.08
     hostel
    0.08
    prend
    0.08
    lor
    0.08
    hood
    0.08
     Metropolitan
    0.08
    å°ıæŶ
    0.08
    /etc
    0.08
     convent
    0.08
    Activations Density 0.037%

    No Known Activations