© 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. 62770
    Prev
    Next
    INDEX
    Explanations

    year or elections

    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
    heim
    -0.08
    isher
    -0.08
    à¸ģระà¸Ī
    -0.08
    Speech
    -0.08
    reira
    -0.08
    IDES
    -0.08
    emean
    -0.08
    _titles
    -0.08
    æīĭ
    -0.08
    ä¸Ģ项
    -0.08
    POSITIVE LOGITS
    éķ¿æķĪ
    0.10
    æĬĹè®®
    0.10
    çĥŃæ½®
    0.09
    æĸ°ä¸Ģè½®
    0.09
    æŶæķĪ
    0.09
    éħ¬
    0.09
    æĿ¥ä¸´
    0.09
    æĮŀ
    0.09
    åIJ¸åħ¥
    0.09
    æ£ĢéªĮ
    0.08
    Activations Density 0.085%

    No Known Activations