© 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. 2576
    Prev
    Next
    INDEX
    Explanations

    RSS feed URLs

    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
    igated
    -0.26
    iage
    -0.25
    ETA
    -0.25
    chai
    -0.25
    ndern
    -0.23
    ynch
    -0.22
    anship
    -0.22
     decoded
    -0.22
     Levy
    -0.22
    åı£å¾Ħ
    -0.22
    POSITIVE LOGITS
     Consortium
    0.28
     bookmark
    0.26
    /XML
    0.25
     Egg
    0.24
    çľ·
    0.24
     Messenger
    0.24
    æİĴæ¯Ĵ
    0.23
    çŃīæĸ¹å¼ı
    0.23
     bookmarks
    0.22
    æ¶Įçİ°
    0.22
    Activations Density 0.003%

    No Known Activations