© 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. 60939
    Prev
    Next
    INDEX
    Explanations

    investment banking and private banking

    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
     hum
    -0.10
    飵
    -0.10
    Hum
    -0.09
    çĽijçĭ±
    -0.09
    ä¸Ī夫
    -0.09
     Hum
    -0.09
     humidity
    -0.09
    shed
    -0.09
    hum
    -0.09
     humid
    -0.09
    POSITIVE LOGITS
    麻
    0.10
    yr
    0.09
    æĪij说
    0.08
     Booster
    0.08
    orest
    0.08
    Monkey
    0.08
    大åݦ
    0.08
    ä¸ĸ家
    0.08
    urd
    0.08
    é²°
    0.08
    Activations Density 0.040%

    No Known Activations