© 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. 53183
    Prev
    Next
    INDEX
    Explanations

    different types or quantities

    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
    æĹ¥ä¸ĬåįĪ
    -0.09
    oba
    -0.09
    som
    -0.08
    åĽłä¸º
    -0.08
    medium
    -0.08
    ILT
    -0.08
    umer
    -0.08
    ãģĵãģ¨ãģ«
    -0.08
    _CA
    -0.08
     som
    -0.07
    POSITIVE LOGITS
    çī¹å®ļ
    0.16
    ä¸įåIJĮç±»åŀĭ
    0.14
     various
    0.14
    çļĦåIJĦç§į
    0.14
    åIJĦ个
    0.14
    ä¸įåIJĮçļĦ
    0.14
    çļĦä¸įåIJĮ
    0.13
    ä¸įåIJĮ
    0.13
     different
    0.13
     اÙĦÙħختÙĦÙģØ©
    0.13
    Activations Density 0.712%

    No Known Activations