© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 63956
    Prev
    Next
    INDEX
    Explanations

    future goals and aspirations

    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
    Negative Logits
    ivec
    -0.08
    è¿Ļåĩł
    -0.08
    é¾Ľ
    -0.08
    æīĵåĩ»
    -0.08
    éĢīæĭ©äºĨ
    -0.08
    è·Įçł´
    -0.08
    çªģåıij
    -0.08
    .normalized
    -0.08
    æ³¢
    -0.08
     mun
    -0.08
    POSITIVE LOGITS
    å°ĨæĿ¥
    0.18
    æľªæĿ¥
    0.15
    åľ¨æľªæĿ¥
    0.15
     future
    0.14
     someday
    0.13
    å¥ĭæĸĹ缮æłĩ
    0.13
    缮æłĩ
    0.13
     goal
    0.13
    缮æ¨Ļ
    0.13
    åıijå±ķ缮æłĩ
    0.12
    Activations Density 0.044%

    No Known Activations