© 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. 627
    Prev
    Next
    INDEX
    Explanations

    personalized or personalised

    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
    ன
    -0.19
    åľºä¸Ĭ
    -0.19
    们çļĦ
    -0.19
    ä¸įå®ī
    -0.18
    é¡¿
    -0.18
    æ´¾åĩº
    -0.18
    наÑĨи
    -0.17
    Paste
    -0.17
    ski
    -0.17
     Levi
    -0.17
    POSITIVE LOGITS
    ../
    0.26
     greetings
    0.23
    åįģ足
    0.23
     welcome
    0.21
     greeting
    0.21
    好æ¶Īæģ¯
    0.21
    ../../../../
    0.20
    och
    0.20
    isable
    0.20
    mad
    0.20
    Activations Density 0.010%

    No Known Activations