© 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. 2804
    Prev
    Next
    INDEX
    Explanations

    screen input

    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
    太åIJİ
    -0.09
    讯
    -0.09
    ä¸įçŁ¥ä¸į
    -0.08
    è¢«åĽ°
    -0.08
    顺
    -0.08
     ÑģамоÑģÑĤоÑıÑĤелÑĮно
    -0.08
    念
    -0.08
    大å®Ĺ
    -0.08
    atz
    -0.08
    é¤IJæ¡Į
    -0.08
    POSITIVE LOGITS
    åIJ»
    0.10
    åijµ
    0.10
    _metadata
    0.09
    人èĦ¸
    0.09
    Interop
    0.09
     Vega
    0.09
    èµ°è¿ij
    0.08
    æģ¹
    0.08
    æľĢä¼ĺ
    0.08
    hest
    0.08
    Activations Density 0.248%

    No Known Activations