© 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. 10687
    Prev
    Next
    INDEX
    Explanations

    i have a

    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
    åĪĿ次
    -0.09
    çŀ»
    -0.09
    å¤
    -0.09
     initially
    -0.09
    omen
    -0.09
    åı«æĪij
    -0.08
     ÑĢÑĥк
    -0.08
    Õ¤
    -0.08
    è£Ĥ
    -0.08
    å°ı鸣
    -0.08
    POSITIVE LOGITS
    çĭIJ
    0.11
    欹
    0.09
    çĮ¾
    0.09
    æ´Ĵ
    0.09
    olem
    0.09
    autiful
    0.09
     ÑģейÑĩаÑģ
    0.08
    èĩ³ä»Ĭ
    0.08
    åIJį家
    0.08
    éªı
    0.08
    Activations Density 0.116%

    No Known Activations