© 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. 57415
    Prev
    Next
    INDEX
    Explanations

    legal documents or filings

    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
    ihan
    -0.08
     Haven
    -0.08
    rror
    -0.08
     intercept
    -0.08
    ело
    -0.08
     Sed
    -0.07
    بÙĪر
    -0.07
     höch
    -0.07
    |RF
    -0.07
    kur
    -0.07
    POSITIVE LOGITS
    éĺħ读åħ¨æĸĩ
    0.11
    åijĬè¯ī大家
    0.10
    ç»Ĭ
    0.09
    第ä¸Ģå±Ĭ
    0.09
    ä»ĸ说
    0.09
    çĶ»åį·
    0.09
    çŀ¥
    0.09
    çĥŁèįī
    0.09
    ç»®
    0.08
    é¢ĨæĤŁ
    0.08
    Activations Density 0.089%

    No Known Activations