© 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. 4504
    Prev
    Next
    INDEX
    Explanations

    Bureau of

    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
    sWith
    -0.10
    æ°ijå¿ĥ
    -0.10
    nes
    -0.09
    iable
    -0.09
     ׼ף
    -0.09
     оÑĢганизм
    -0.09
    IMUM
    -0.09
    å·¥ä¸ļ大åѦ
    -0.09
    Resizable
    -0.09
    ãĥ³ãĤ°
    -0.09
    POSITIVE LOGITS
    ÑĪиб
    0.11
    naire
    0.10
    åĵ¡
    0.10
    ÑģÑĤÑĮ
    0.10
    åIJı
    0.10
     Downs
    0.09
    anson
    0.09
    窿
    0.09
     impro
    0.09
    itarian
    0.09
    Activations Density 0.013%

    No Known Activations