© 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. 23693
    Prev
    Next
    INDEX
    Explanations

    power electronic devices converter

    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
     Eig
    -0.08
    èļķ
    -0.08
    fac
    -0.08
    snippet
    -0.08
    縻
    -0.08
     mechanic
    -0.08
    å¦ĥ
    -0.08
    åıĨ
    -0.08
    æĮĩ示
    -0.07
     Cooper
    -0.07
    POSITIVE LOGITS
    è°ĥçIJĨ
    0.11
    纹
    0.10
     пÑĢе
    0.10
    åIJīåĪ©
    0.09
    çĤķ
    0.09
    пÑĢе
    0.09
    æĬĬæĮģ
    0.09
    -Control
    0.09
    ç´ĭ
    0.09
    çłģ头
    0.09
    Activations Density 0.180%

    No Known Activations