© 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. 10952
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers and positions

    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
    lem
    -0.10
    åıijåŀĭ
    -0.10
    èĮİ
    -0.10
    åħ¬åħ±æĸĩåĮĸ
    -0.09
    ä»ĬçĶŁ
    -0.09
    æĢ§å¼º
    -0.09
    æĮŀ
    -0.09
    橱
    -0.09
    èĻ±
    -0.09
    åĿŀ
    -0.09
    POSITIVE LOGITS
    ä¸įåĬ¨
    0.08
    habi
    0.08
    IfNeeded
    0.08
    ÑĢова
    0.08
    ropp
    0.08
    并ä¸İ
    0.07
    æĿ³
    0.07
    ompson
    0.07
    ë§Ŀ
    0.07
    _estimate
    0.07
    Activations Density 0.004%

    No Known Activations