© 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. 48264
    Prev
    Next
    INDEX
    Explanations

    leading or taking initiative

    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
    çļĦå®ŀåĬĽ
    -0.09
    ä¿®åħ»
    -0.09
    æĻļ
    -0.08
    aison
    -0.08
    ä½ŀ
    -0.08
    çļĦéĴ±
    -0.08
     нап
    -0.08
    _EV
    -0.08
    æķĹ
    -0.08
    ude
    -0.08
    POSITIVE LOGITS
    å¼ķé¢Ĩ
    0.19
    带头
    0.18
    é¢Ĩè·ij
    0.17
    é¢Ĩè¡Ķ
    0.16
    çīµå¤´
    0.15
    çļĦ带é¢Ĩä¸ĭ
    0.15
    é¢ĨåħĪçļĦ
    0.15
    åħĪ导
    0.14
    é¢ĨåħĪ
    0.14
    èµ°åľ¨
    0.14
    Activations Density 0.048%

    No Known Activations