© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 897
    Prev
    Next
    INDEX
    Explanations

    criteria and guidelines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
     Matters
    -0.24
    ä¸Ńæ¯Ĵ
    -0.23
    ault
    -0.22
    oline
    -0.22
     shorthand
    -0.22
    讲究
    -0.21
    æĸĩåĮĸ
    -0.21
    DI
    -0.21
    lette
    -0.20
     coeff
    -0.20
    POSITIVE LOGITS
    è¡Įäºĭ
    0.32
    åĬŀäºĭ
    0.26
    èĢĮåĩº
    0.26
    åİ»åģļ
    0.25
    èĢĮä¸į
    0.24
    ä¸įåĬ¨
    0.24
    ëĮĢë¡ľ
    0.24
    æľĢå¤ļçļĦ
    0.23
    \""
    0.23
    Sizer
    0.22
    Activations Density 0.164%

    No Known Activations