© 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. 1192
    Prev
    Next
    INDEX
    Explanations

    magnificent property

    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
    Č↵
    -0.25
    éĤ£äºº
    -0.24
    æŦ
    -0.23
    ril
    -0.23
    ç³Ĭ
    -0.23
    读åIJİ
    -0.23
    umat
    -0.22
    alice
    -0.22
    :Object
    -0.22
    |=↵
    -0.22
    POSITIVE LOGITS
    ä¼Ĭå§ĭ
    0.25
    é«ĺåĵģè´¨
    0.25
    幸è¿IJ
    0.24
     Presented
    0.24
     Silent
    0.22
     proudly
    0.22
    ä½ĵéªĮ
    0.22
    åħ¨æĸ¹ä½į
    0.22
    lad
    0.21
     Beat
    0.21
    Activations Density 0.003%

    No Known Activations