© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2518
    Prev
    Next
    INDEX
    Explanations

    Stamboul

    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
    udu
    -0.25
    inspace
    -0.24
    ndo
    -0.23
     steep
    -0.23
    UILayout
    -0.23
    æ²Ļ滩
    -0.23
    nton
    -0.22
    åĿ¯
    -0.22
    绿水
    -0.21
    inders
    -0.21
    POSITIVE LOGITS
    ember
    0.24
     Dropdown
    0.23
    /XML
    0.23
    èī²æĥħ
    0.23
     mimetype
    0.23
    çīĪæľ¬
    0.22
    allback
    0.22
     XML
    0.22
     perse
    0.22
     dll
    0.22
    Activations Density 0.085%

    No Known Activations