© 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. 23561
    Prev
    Next
    INDEX
    Explanations

    happening or existing

    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
    TestData
    -0.09
    sez
    -0.09
    CHIP
    -0.09
    æݧåĪ¶åĻ¨
    -0.09
    梦è§ģ
    -0.09
    tok
    -0.09
    issy
    -0.09
    ãĤ«ãĥ¡
    -0.09
    .toolbox
    -0.09
    esis
    -0.09
    POSITIVE LOGITS
    æĻ¯èī²
    0.08
    æŁĺ
    0.08
    çļĦåIJĦ项
    0.08
     благодаÑĢÑı
    0.08
    pired
    0.08
    åĽ´ç»ķ
    0.08
    åħ³äºİæĪij们
    0.08
    æĹ¢æĺ¯
    0.08
    orus
    0.08
    èĻij
    0.08
    Activations Density 0.100%

    No Known Activations