© 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. 38868
    Prev
    Next
    INDEX
    Explanations

    apigateway, Lambda, NodeJS

    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
    ä¸Ģç¬Ķ
    -0.10
    åĬ¡
    -0.10
    sleep
    -0.09
    ä¹ĭä½ľ
    -0.09
     dic
    -0.09
    dic
    -0.09
    _SLEEP
    -0.09
    .sleep
    -0.08
    çī¢åĽº
    -0.08
    æķĻèĤ²æķĻåѦ
    -0.08
    POSITIVE LOGITS
    éĶĢåĶ®æĶ¶åħ¥
    0.11
    éļı
    0.10
    æĦļ
    0.10
    zell
    0.10
     Jonas
    0.09
    éļıæīĭ
    0.09
    Authority
    0.09
    SA
    0.09
    asel
    0.09
    otto
    0.09
    Activations Density 0.148%

    No Known Activations