© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35972
    Prev
    Next
    INDEX
    Explanations

    Mary and Simon

    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
    åĵ¨
    -0.11
     Constitutional
    -0.09
    æľį
    -0.09
    糧
    -0.09
    ester
    -0.09
    çļĦæĹ¥åŃIJéĩĮ
    -0.09
     constitutional
    -0.09
    trap
    -0.09
    欺
    -0.09
     Terrace
    -0.08
    POSITIVE LOGITS
     wom
    0.10
    rette
    0.09
    æĬ¹
    0.09
    æ½ľæ°´
    0.09
    ExecutionContext
    0.09
    _soc
    0.09
    ridor
    0.08
    .central
    0.08
    æĪIJåijĺåįķä½į
    0.08
    öl
    0.08
    Activations Density 0.019%

    No Known Activations