© 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. 1967
    Prev
    Next
    INDEX
    Explanations

    coupon codes

    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
    KHTML
    -0.26
    .rdf
    -0.25
    DSA
    -0.23
     ÑģебÑı
    -0.23
    idy
    -0.23
     Ñĥме
    -0.22
    redicate
    -0.21
    lâ
    -0.21
     Assertion
    -0.21
     imagin
    -0.20
    POSITIVE LOGITS
    ile
    0.27
    eper
    0.27
    ilers
    0.26
    äºĭåIJİ
    0.24
    害
    0.24
    ä¿ĥéĶĢ
    0.23
    daily
    0.22
    åĢ¼å¾Ĺ
    0.22
    æĺ¯ä»Ģä¹Īåij¢
    0.21
    ä¼ĺæĥł
    0.21
    Activations Density 0.003%

    No Known Activations