© 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. 22560
    Prev
    Next
    INDEX
    Explanations

    amazed, surprised, impressed, convincing

    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
    squ
    -0.10
     Locker
    -0.10
    ç¬Ķ
    -0.09
    BOOST
    -0.08
     занÑıÑĤ
    -0.08
    è´¨
    -0.08
    梳çIJĨ
    -0.08
    ãģ«ãģ¤
    -0.08
    ä»ĺ
    -0.08
    äºĴåĬ©
    -0.08
    POSITIVE LOGITS
    å¾ģæľį
    0.15
     surprise
    0.14
     surprises
    0.12
     impressed
    0.12
    æĦŁåĬ¨
    0.12
    æĥĬåĸľ
    0.12
    æĥĬ讶
    0.11
    æīĵåĬ¨
    0.11
    æĥĬå¥ĩ
    0.11
     surprised
    0.11
    Activations Density 0.071%

    No Known Activations