© 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. 63082
    Prev
    Next
    INDEX
    Explanations

    finance and news outlets

    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
    èĨ³
    -0.09
    æ±°
    -0.09
     pigeon
    -0.09
    æıĨ
    -0.09
    辨åĪ«
    -0.09
     hare
    -0.09
    溪
    -0.08
    ilha
    -0.08
    adders
    -0.08
    澳大
    -0.08
    POSITIVE LOGITS
    注æĺİæĿ¥æºIJ
    0.09
    ç«ĭæĸ¹
    0.09
    iei
    0.09
    è´§
    0.09
    paths
    0.09
    貨
    0.08
    inde
    0.08
    èĵĵ
    0.08
    ÑĢаг
    0.08
     пен
    0.08
    Activations Density 0.009%

    No Known Activations