© 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. 10041
    Prev
    Next
    INDEX
    Explanations

    places and venues

    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
    ç§Ģ
    -0.09
    pository
    -0.08
    uttle
    -0.08
    å¼Ĥ
    -0.08
    positories
    -0.08
    orget
    -0.08
    é¹Į
    -0.08
    SION
    -0.08
    å¼
    -0.08
     Mam
    -0.08
    POSITIVE LOGITS
    æĿ¿åĿĹ
    0.11
    涵
    0.10
    éģĺ
    0.10
    å·¥åºı
    0.09
    çݯèĬĤ
    0.09
    æ¾¹
    0.09
     patron
    0.09
     subsidiary
    0.09
    ä¸ĵåľº
    0.09
     Blanch
    0.09
    Activations Density 0.647%

    No Known Activations