© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29422
    Prev
    Next
    INDEX
    Explanations

    charitable organizations and beneficiaries

    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
    Negative Logits
    夹
    -0.10
    çĪ¹
    -0.09
    antan
    -0.09
    .statistics
    -0.09
    erie
    -0.08
    æĭ
    -0.08
    é³Ħ
    -0.08
    å¤
    -0.08
    åįļæĸĩ
    -0.08
    6
    -0.08
    POSITIVE LOGITS
    æ³ł
    0.09
    äºĭä¸ļåıijå±ķ
    0.09
    åŁºæľ¬åİŁåĪĻ
    0.09
    å¤ļå°ijéĴ±
    0.09
    éĨ¢
    0.09
    มหา
    0.08
    éĿ¶
    0.08
    çļĦèµĦéĩij
    0.08
    å¯ĴåĨ·
    0.08
    enthal
    0.08
    Activations Density 0.041%

    No Known Activations