© 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. 59126
    Prev
    Next
    INDEX
    Explanations

    places with Arabic names

    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
     Timothy
    -0.09
    uth
    -0.08
    BAB
    -0.08
    åĵģ
    -0.08
     BAB
    -0.08
    orns
    -0.08
    oras
    -0.08
    _lock
    -0.08
    æľīå¾Ī大
    -0.08
    ORN
    -0.08
    POSITIVE LOGITS
    anse
    0.10
    åģĥ
    0.10
    å¥
    0.09
    é¹³
    0.09
    ãģĹãģ¦ãģĬãģı
    0.09
    æĬ±
    0.09
    éĶ¦ç»£
    0.09
    鹤
    0.08
    西æ´ĭ
    0.08
    à¹Ĥà¸Ľ
    0.08
    Activations Density 0.041%

    No Known Activations