© 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. 54158
    Prev
    Next
    INDEX
    Explanations

    virginity or purity

    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
    ODO
    -0.09
    ä¼Ļ
    -0.09
     Fat
    -0.08
    ä¸Ģæĺ¯
    -0.08
    å©ļ姻
    -0.08
     fat
    -0.08
    æľªç»ıæİĪæĿĥ
    -0.08
    Fat
    -0.08
     Apt
    -0.08
    :nil
    -0.08
    POSITIVE LOGITS
    é¢ĸ
    0.10
    央
    0.09
    existent
    0.09
    iasco
    0.09
    tempts
    0.08
    ç¾ŀ
    0.08
    æµ·å°Ķ
    0.08
    té
    0.08
    NCY
    0.08
     berg
    0.08
    Activations Density 0.147%

    No Known Activations