© 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. 33344
    Prev
    Next
    INDEX
    Explanations

    money or worth

    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
    uppe
    -0.09
    ç¼ł
    -0.09
    ä¹ĭåŁİ
    -0.09
    颤æĬĸ
    -0.09
    ãģ¹ãģį
    -0.09
    ÙħÙĦ
    -0.09
    ä¸įäºĨ
    -0.09
    ارÙĬ
    -0.09
    æľ¬æľĪ
    -0.08
     COPYRIGHT
    -0.08
    POSITIVE LOGITS
    ILA
    0.08
    ulty
    0.08
    маг
    0.08
    ÑĦин
    0.08
    ila
    0.08
     Catal
    0.07
    çĪ¹
    0.07
    æİī
    0.07
    åĴ±
    0.07
    çijĽ
    0.07
    Activations Density 0.320%

    No Known Activations