© 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. 39130
    Prev
    Next
    INDEX
    Explanations

    whopping or young age

    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
    纽
    -0.11
    åºľ
    -0.09
    å¯Ł
    -0.09
    зал
    -0.09
    èĵ®
    -0.09
    ancock
    -0.09
    ẻ
    -0.09
    ê¶Į
    -0.09
    _memcpy
    -0.09
    éģ¿
    -0.09
    POSITIVE LOGITS
    尤为
    0.09
    æķ´æķ´
    0.08
     mere
    0.08
    mere
    0.08
    æĿī
    0.08
    imers
    0.08
    åıªæľī
    0.08
    ãģªãĤĵãģ¨
    0.08
     whopping
    0.08
    ç«ŁçĦ¶
    0.08
    Activations Density 0.087%

    No Known Activations