© 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. 53787
    Prev
    Next
    INDEX
    Explanations

    financial instruments and payments

    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
    æ´¥
    -0.13
    æī¶
    -0.09
    lbl
    -0.09
     одно
    -0.09
    sit
    -0.08
    å»ĵ
    -0.08
    auer
    -0.08
    éħį
    -0.08
    ç´¯äºĨ
    -0.08
    åĢĻ
    -0.08
    POSITIVE LOGITS
    sto
    0.09
    é»ĺ
    0.09
    ç½ijç»ľä¼łæĴŃ
    0.08
    ç¥ī
    0.08
    ç½²
    0.08
     Sto
    0.08
    èħ¹éĥ¨
    0.08
     lÆ°ng
    0.08
     abbreviation
    0.08
    åıį对
    0.08
    Activations Density 0.002%

    No Known Activations