© 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. 3379
    Prev
    Next
    INDEX
    Explanations

    language, indigenous, culture

    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
    éĥ¦
    -0.09
    å¿ł
    -0.09
    天é¹ħ
    -0.09
    çĽijå¯Ł
    -0.08
    ç»ıèIJ¥çIJĨ念
    -0.08
    æĬĹåĩ»
    -0.08
     Phrase
    -0.08
    åı¯ä»¥æĽ´å¥½
    -0.08
    æĽ´å¥½çļĦ
    -0.08
    æľĶ
    -0.08
    POSITIVE LOGITS
    ç³»æķ°
    0.09
    å¤ĩçĶ¨
    0.09
    磴
    0.09
    æĵĤ
    0.09
    ObjectName
    0.09
    bane
    0.09
    åħ¼
    0.09
    禳
    0.09
    æĺĢ
    0.09
    изм
    0.09
    Activations Density 0.150%

    No Known Activations