© 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. 40421
    Prev
    Next
    INDEX
    Explanations

    tax deductions and exemptions

    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
    pad
    -0.10
    strap
    -0.09
    çķ¹
    -0.09
    海绵
    -0.08
    管çIJĨæ°´å¹³
    -0.08
    å¼Ħ
    -0.08
    åĨħéĥ¨æݧåĪ¶
    -0.08
    erton
    -0.08
    .ta
    -0.08
    管çIJĨ模å¼ı
    -0.08
    POSITIVE LOGITS
    çľĭä¸įåĪ°
    0.10
    itizer
    0.10
    OPY
    0.10
    OST
    0.10
     thượng
    0.09
     limitless
    0.09
    æĵ
    0.09
     IOS
    0.09
    ost
    0.09
    å³Ń
    0.09
    Activations Density 0.003%

    No Known Activations