© 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. 906
    Prev
    Next
    INDEX
    Explanations

    character encoding

    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
    fluid
    -0.24
    ECH
    -0.24
    æį¢å±Ĭ
    -0.24
    posal
    -0.23
     Survival
    -0.23
    人æ°ijåĮ»éĻ¢
    -0.23
     survival
    -0.22
    bserv
    -0.22
    ivet
    -0.22
     contrat
    -0.22
    POSITIVE LOGITS
     glyph
    0.32
     letters
    0.31
     lingu
    0.30
    åŃĹ
    0.28
     linguistic
    0.27
     glyphs
    0.27
     alph
    0.27
    æĭ¼éŁ³
    0.27
     бÑĥк
    0.27
     word
    0.26
    Activations Density 0.007%

    No Known Activations