© 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. 18665
    Prev
    Next
    INDEX
    Explanations

    let us / let's

    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
    åijĨ
    -0.09
    è¦ģåĿļæĮģ
    -0.09
    æĹ»
    -0.08
    UnitOfWork
    -0.08
    ä¸įè¿ľ
    -0.08
     ×ŀ×ij
    -0.08
    ddl
    -0.08
     shut
    -0.08
    æŃ£åĵģ
    -0.07
    tro
    -0.07
    POSITIVE LOGITS
    unic
    0.12
    æī£éĻ¤
    0.10
    æĿ¥æī¾
    0.09
    ASTER
    0.09
    帮åĬ©ä¼ģä¸ļ
    0.09
    å¸®ä½ł
    0.08
    éŨåı£
    0.08
    为æĪij们
    0.08
    让æĪij们
    0.08
    .Serve
    0.08
    Activations Density 0.021%

    No Known Activations