© 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. 738
    Prev
    Next
    INDEX
    Explanations

    Nokia, Lumia, Xiaomi, Fiat, Helsinki

    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
     Verg
    -0.09
    ÑĥÑī
    -0.09
    ly
    -0.08
    çĶŁèĤĸ
    -0.08
    iqu
    -0.08
    ément
    -0.08
    ussen
    -0.08
    oes
    -0.08
    åªĴ
    -0.08
    ritt
    -0.08
    POSITIVE LOGITS
    thon
    0.10
     dáng
    0.10
    itchens
    0.09
    ular
    0.09
    èĬ¬åħ°
    0.09
     Lumia
    0.09
    à¹ģà¸Ľà¸¥
    0.09
    æĹ¶ç©º
    0.09
    ä¸ĢæĹı
    0.09
     Guinness
    0.09
    Activations Density 0.003%

    No Known Activations