© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59164
    Prev
    Next
    INDEX
    Explanations

    completion or done status

    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
    sWith
    -0.12
    à¹Į
    -0.12
    craft
    -0.11
    wide
    -0.10
    ãģĦãģ¾ãģĻ
    -0.10
    æĸĩ娱
    -0.09
    tool
    -0.09
    ly
    -0.09
    ized
    -0.09
    mit
    -0.09
    POSITIVE LOGITS
    æĨ¬
    0.11
    ests
    0.10
    xygen
    0.10
    ctors
    0.10
    abant
    0.09
    ze
    0.09
    leine
    0.09
    åŁĴ
    0.09
    umeric
    0.09
    velop
    0.09
    Activations Density 0.018%

    No Known Activations