© 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. 38646
    Prev
    Next
    INDEX
    Explanations

    equal, peer, par

    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
    .digest
    -0.08
    outh
    -0.08
    常å·ŀ
    -0.08
    istica
    -0.08
    _locator
    -0.08
    è¿ĺæĺ¯
    -0.08
    æĦı大
    -0.08
    çľģ
    -0.07
    Hay
    -0.07
    å¿łå®ŀ
    -0.07
    POSITIVE LOGITS
    å¹³çŃī
    0.15
    åIJĮçŃī
    0.13
    åľ°ä½į
    0.12
    ÑĢав
    0.10
     ÑĢав
    0.10
     equality
    0.10
    åįij
    0.09
    agoon
    0.09
    è¯Ŀè¯ŃæĿĥ
    0.09
    éĴĹ
    0.09
    Activations Density 0.059%

    No Known Activations