© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37372
    Prev
    Next
    INDEX
    Explanations

    The Wars or Lost Memories

    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
    人äºĭ
    -0.09
    ushman
    -0.09
    åIJĪåĬĽ
    -0.09
    chor
    -0.09
    ius
    -0.09
    éķ¿å¯¿
    -0.08
    cript
    -0.08
    寿
    -0.08
    æĿ¯
    -0.08
     dorsal
    -0.08
    POSITIVE LOGITS
    istro
    0.09
    èµ°ä¸ĭåİ»
    0.09
    umin
    0.09
    æĹĹèĪ°
    0.09
    çļĦä¸Ģç§į
    0.08
    æīĭæľºçīĪ
    0.08
    äº
    0.08
     Clo
    0.08
    erk
    0.08
    移æ°ij
    0.08
    Activations Density 0.196%

    No Known Activations