© 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. 31521
    Prev
    Next
    INDEX
    Explanations

    surrounding or surrounded by something

    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
    zell
    -0.09
    sse
    -0.09
    eries
    -0.09
    çĪ¿
    -0.09
    itud
    -0.09
    à¸Ķำ
    -0.08
    erv
    -0.08
    -0.08
    меÑĢ
    -0.08
    黥
    -0.08
    POSITIVE LOGITS
     Ñģобой
    0.13
    åĽ¹
    0.11
    iveness
    0.11
    ry
    0.10
    ä¸Ģ群
    0.10
    æ°Ľ
    0.10
    /interface
    0.09
    à¹ģ
    0.09
    ientes
    0.09
    大大å°ıå°ı
    0.09
    Activations Density 0.017%

    No Known Activations