© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22204
    Prev
    Next
    INDEX
    Explanations

    coding: utf-8

    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
    ä¸Ģå¿ĥ
    -0.09
    黣
    -0.08
    æķ
    -0.08
    uter
    -0.08
    isters
    -0.08
    atu
    -0.08
    èIJ½å®ŀ
    -0.08
    æģŃ
    -0.08
    Sdk
    -0.08
    ateurs
    -0.08
    POSITIVE LOGITS
     utf
    0.11
    =UTF
    0.11
    (encoding
    0.10
    .utf
    0.10
    utf
    0.10
     encoding
    0.10
    _ENCODING
    0.10
     Encoding
    0.10
    .UTF
    0.10
    ernet
    0.09
    Activations Density 0.226%

    No Known Activations