© 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. 32497
    Prev
    Next
    INDEX
    Explanations

    Indian cities and states

    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
    ynes
    -0.10
    éļıå¤Ħ
    -0.10
    åı¬
    -0.10
    amon
    -0.09
    审åĪ¤
    -0.09
    åįİåĮĹ
    -0.09
    åı¬éĽĨ
    -0.08
    åĮĹæŀģ
    -0.08
    åĮĪ奴
    -0.08
    çķ¿
    -0.08
    POSITIVE LOGITS
    åľ¨ä¸Ĭæµ·
    0.13
    沪
    0.12
     Chicago
    0.11
    éĩįåºĨå¸Ĥ
    0.11
     Maharashtra
    0.11
    èŁł
    0.11
    èĪŁå±±
    0.11
     Pune
    0.11
     Mumbai
    0.10
    æ¸Ŀ
    0.10
    Activations Density 0.091%

    No Known Activations