© 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. 53122
    Prev
    Next
    INDEX
    Explanations

    Miz and biz variations

    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
    ially
    -0.12
    uden
    -0.11
    zelf
    -0.10
    -quarters
    -0.09
    ides
    -0.09
    Notifier
    -0.09
    IJľ
    -0.09
    боÑĢ
    -0.09
    ä¸įäºĨ
    -0.09
    /or
    -0.09
    POSITIVE LOGITS
    ellaneous
    0.11
    ä¸ĢåĽ¢
    0.09
    adow
    0.09
    chor
    0.09
    typ
    0.09
    ãĥĪãĥĥãĥĹ
    0.09
    èįĩ
    0.09
    RARY
    0.09
    grad
    0.09
    å°ıäºĭ
    0.09
    Activations Density 0.024%

    No Known Activations