© 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. 31330
    Prev
    Next
    INDEX
    Explanations

    Indian city names and languages

    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
    ski
    -0.09
    -0.08
    åħ¶ä»ĸçļĦ
    -0.08
    rog
    -0.08
    ahr
    -0.08
    orthy
    -0.07
    åIJĦèĩªçļĦ
    -0.07
    ä»İèĢĮ使
    -0.07
    osl
    -0.07
     Miscellaneous
    -0.07
    POSITIVE LOGITS
    å¥ļ
    0.10
    äºĮåŃĹ
    0.10
    çķĢ
    0.09
    éĿŀ常好
    0.09
    ä¼¼
    0.09
    uil
    0.09
    å¥ł
    0.09
    åŁĴ
    0.09
    çĦī
    0.09
    å¼ºåĽ½
    0.08
    Activations Density 0.034%

    No Known Activations