© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 335
    Prev
    Next
    INDEX
    Explanations

    menu navigation

    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
    elts
    -0.26
     blanks
    -0.25
    etty
    -0.24
     itself
    -0.23
    伪
    -0.23
     alike
    -0.23
     Cain
    -0.22
    fdc
    -0.22
    ocator
    -0.22
    ä¿Ĺ
    -0.21
    POSITIVE LOGITS
    çĦ¶åIJİ
    0.34
    çĦ¶åIJİåĨį
    0.27
    çĦ¶å¾Į
    0.27
     menu
    0.24
    çķĻä½ı
    0.23
    /power
    0.23
     Trustees
    0.23
    èĢĮåIJİ
    0.23
     fullscreen
    0.23
    utra
    0.23
    Activations Density 0.033%

    No Known Activations