© 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. 47
    Prev
    Next
    INDEX
    Explanations

    numbers and roman numerals

    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
    .").
    -0.26
    aptive
    -0.23
    CAPE
    -0.22
    .).↵↵
    -0.22
    ropp
    -0.21
    ï¼īãĢĤ
    -0.21
    ellery
    -0.21
    oric
    -0.21
    SAM
    -0.21
    Lets
    -0.21
    POSITIVE LOGITS
    URN
    0.23
    åĢĴéĹŃ
    0.22
    _rem
    0.22
    è¿ĻäºĽéĥ½æĺ¯
    0.21
    è§Ħå¾ĭ
    0.21
    ollo
    0.20
     inf
    0.20
    åĢĴåľ¨
    0.20
     bills
    0.20
    lev
    0.19
    Activations Density 0.290%

    No Known Activations