© 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. 58440
    Prev
    Next
    INDEX
    Explanations

    national park

    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
    æ¡£
    -0.09
    æ³ķå¾ĭ责任
    -0.09
    æªĶ
    -0.09
    身æĹģ
    -0.09
    ãģĥ
    -0.09
    主æĦı
    -0.09
    ãģľ
    -0.09
    scheme
    -0.08
    ëŀĢ
    -0.08
     quake
    -0.08
    POSITIVE LOGITS
    èĸ®
    0.10
    aroo
    0.10
    wide
    0.09
    /sites
    0.09
    é¹Ī
    0.09
    itecture
    0.09
    stead
    0.09
    rupt
    0.09
    çĹª
    0.09
    dated
    0.08
    Activations Density 0.010%

    No Known Activations