© 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. 63404
    Prev
    Next
    INDEX
    Explanations

    at the

    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
     chances
    -0.08
    ething
    -0.08
     duties
    -0.08
    è¿Ļè¾ĪåŃIJ
    -0.08
    ning
    -0.08
    æĸ¯é¡¿
    -0.08
    nal
    -0.08
     gì
    -0.08
    iture
    -0.08
    issen
    -0.08
    POSITIVE LOGITS
    à¹Ħหà¸Ļ
    0.11
    ween
    0.10
    ников
    0.10
    ä¸ĢæŶ
    0.10
    год
    0.10
     ÙħÙĤابÙĦ
    0.09
    å¾Īé«ĺçļĦ
    0.09
    fel
    0.09
     ÑįлекÑĤÑĢо
    0.09
    æıĸ
    0.09
    Activations Density 0.088%

    No Known Activations