© 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. 11523
    Prev
    Next
    INDEX
    Explanations

    improvisation and improvement

    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
    paces
    -0.10
    é¼ĵèĪŀ
    -0.09
    ä¸ĭæ»ij
    -0.09
    ĺ
    -0.09
    rch
    -0.09
    rum
    -0.09
    æĻ®æŁ¥
    -0.09
    ä¸į解
    -0.09
    ompiler
    -0.08
    éĵĽ
    -0.08
    POSITIVE LOGITS
    åĩºæĿ¥çļĦ
    0.10
    诳
    0.09
    åĬ¨éĿĻ
    0.09
    åĪĺæµ·
    0.08
    addin
    0.08
     Cuá»Ļc
    0.08
    çķ´
    0.08
    illis
    0.08
    åľ¨å®¶éĩĮ
    0.08
     Thảo
    0.08
    Activations Density 0.004%

    No Known Activations