© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 54773
    Prev
    Next
    INDEX
    Explanations

    legal and financial terms

    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
     Reviewed
    -0.08
    رات
    -0.08
    åľ¨æѤ
    -0.08
    éĴµ
    -0.07
     ethnic
    -0.07
    wing
    -0.07
    oders
    -0.07
    ipsis
    -0.07
    åħ¨æĸĩ
    -0.07
     Fare
    -0.07
    POSITIVE LOGITS
    lien
    0.10
    串
    0.09
    第ä¸ī人
    0.09
    åķĨ人
    0.09
    æĭįåįĸ
    0.09
    åºĶæĶ¶
    0.09
    çĸı
    0.09
    绿水
    0.09
    æ¯ģçģŃ
    0.09
    渣
    0.09
    Activations Density 0.082%

    No Known Activations