© 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. 47919
    Prev
    Next
    INDEX
    Explanations

    EventGhost Project

    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
    à¹Ģย
    -0.09
    åĪĹåĩº
    -0.09
    æĸ°å±ĢéĿ¢
    -0.09
    ä»·åĢ¼éĵ¾
    -0.09
    çĵľ
    -0.09
    åľ©
    -0.09
    汶
    -0.09
    èĬ±æł·
    -0.08
    æĻ¾
    -0.08
     اÙĦأس
    -0.08
    POSITIVE LOGITS
    身åIJİ
    0.10
    å¾Ħ
    0.09
    åį°è±¡
    0.09
    ç»ıå¼Ģ
    0.09
    æĤīå°¼
    0.09
    rá
    0.09
    .Ma
    0.08
    pine
    0.08
    鹿
    0.08
    indsight
    0.08
    Activations Density 0.008%

    No Known Activations