© 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. 1191
    Prev
    Next
    INDEX
    Explanations

    published within

    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
    weed
    -0.23
    çŁ¥
    -0.23
    TURE
    -0.23
    ceu
    -0.23
    $__
    -0.22
    STACK
    -0.22
     ass
    -0.22
     вÑĭполнÑı
    -0.21
    Ñģк
    -0.21
    èµı
    -0.21
    POSITIVE LOGITS
    åľ¨åħ¨çIJĥ
    0.28
    èĢħãģ¯
    0.23
    æľ¬ç½ijç«Ļ
    0.23
    æľªç»ıæİĪæĿĥ
    0.23
    oir
    0.22
    è¡Ģèħ¥
    0.22
    onis
    0.22
    eren
    0.22
    èĢħçļĦ
    0.22
    ä¸įåIJĪ
    0.22
    Activations Density 0.008%

    No Known Activations