© 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. 5069
    Prev
    Next
    INDEX
    Explanations

    -themed nouns

    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
    第ä¸ĢåIJį
    -0.08
    说å®ŀ
    -0.08
    åħ³äºİ
    -0.08
    оÑĢа
    -0.08
    éĺĮ
    -0.08
    reat
    -0.07
     Tribe
    -0.07
    Facade
    -0.07
    oya
    -0.07
    ToJson
    -0.07
    POSITIVE LOGITS
    为主çļĦ
    0.10
    æIJĵ
    0.09
    ç»ŀ
    0.09
    马路
    0.09
    ibus
    0.09
    éĻĮ
    0.09
    /generated
    0.09
    ç¦Ģ
    0.09
    å±ģèĤ¡
    0.08
    izada
    0.08
    Activations Density 0.137%

    No Known Activations