© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35715
    Prev
    Next
    INDEX
    Explanations

    United States, United Arab Emirates

    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
    activ
    -0.10
    ä¹¾åĿ¤
    -0.10
    æ´
    -0.09
    icl
    -0.09
    è¿Ļä½į
    -0.08
    bau
    -0.08
    严谨
    -0.08
    æĺ¯éĿŀ
    -0.08
    typing
    -0.08
    iali
    -0.08
    POSITIVE LOGITS
     STATES
    0.10
    ales
    0.09
    éĹª
    0.09
     СШÐIJ
    0.09
    .flash
    0.09
    ÑĢей
    0.08
    mixed
    0.08
     Britain
    0.08
    ixed
    0.08
    ë¶Ī
    0.08
    Activations Density 0.088%

    No Known Activations