© 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. 2950
    Prev
    Next
    INDEX
    Explanations

    I say "I"

    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
    对æĪijæĿ¥è¯´
    -0.11
    æĪIJé¾Ļ
    -0.10
    æł¼å¤ĸ
    -0.10
    空åīį
    -0.09
    éºĴéºŁ
    -0.09
    缴åįĩ
    -0.09
    åij¨æģ©
    -0.09
    è¿Ļä¸Ģ次
    -0.09
    欢è¿İ大家
    -0.09
    çŁ³æ¦´
    -0.08
    POSITIVE LOGITS
    OWN
    0.13
    éĤ£æł·çļĦ
    0.12
    çĽ¸ä¼¼
    0.12
    ä¸Ģæł·çļĦ
    0.11
     own
    0.11
    类似çļĦ
    0.11
    羡æħķ
    0.11
    Own
    0.11
     OWN
    0.11
    own
    0.11
    Activations Density 0.097%

    No Known Activations