© 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. 2952
    Prev
    Next
    INDEX
    Explanations

    investment and finance 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
     Standing
    -0.09
     strang
    -0.09
    udit
    -0.09
    ç«Ļç«ĭ
    -0.09
    gor
    -0.09
    AGO
    -0.09
    æĮĩåįĹ
    -0.09
    èµ°
    -0.09
    æ²®
    -0.08
    _EPS
    -0.08
    POSITIVE LOGITS
    解æĶ¾æĢĿæĥ³
    0.10
    é©°æı´
    0.10
    åݦ
    0.09
    æĬ¢æķij
    0.09
    åºĸ
    0.09
    æĪij们认为
    0.09
    主è§Ĥ
    0.09
    å«ĸ
    0.09
    èĥİ
    0.09
    è§īå¾Ĺ
    0.09
    Activations Density 0.055%

    No Known Activations