© 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. 19166
    Prev
    Next
    INDEX
    Explanations

    hind or India related words

    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
    ting
    -0.12
    é¬ĵ
    -0.11
    ç´§åĩij
    -0.10
    otron
    -0.10
    imitives
    -0.09
    è°®
    -0.09
    ãĤĪãģĨãģª
    -0.09
    æ£į
    -0.09
    è¡Įä¸ļåĨħ
    -0.09
    âĻ¤
    -0.09
    POSITIVE LOGITS
    ering
    0.12
    ness
    0.11
    erman
    0.10
    ess
    0.10
    rance
    0.10
    erview
    0.09
    erval
    0.09
    леп
    0.09
    Ñĥ
    0.09
    ergarten
    0.09
    Activations Density 0.012%

    No Known Activations