© 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. 821
    Prev
    Next
    INDEX
    Explanations

    pair with

    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
    交æİ¥
    -0.23
    渺
    -0.23
    ä¸Ģç«Ļ
    -0.23
    procedure
    -0.23
    framework
    -0.22
    implements
    -0.22
    åĪ°æľŁ
    -0.22
     подпиÑģ
    -0.22
    临æŶ
    -0.22
     TempData
    -0.22
    POSITIVE LOGITS
     wines
    0.35
    matcher
    0.34
     restaurant
    0.34
    èij¡èIJĦéħĴ
    0.34
    é¤IJ饮
    0.34
     wine
    0.33
    æIJŃéħį
    0.33
    restaurant
    0.32
    é¤IJåİħ
    0.32
    .restaurant
    0.32
    Activations Density 0.008%

    No Known Activations