© 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. 856
    Prev
    Next
    INDEX
    Explanations

    address bar in browser

    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
    TestData
    -0.28
    éĿ¡
    -0.26
    THR
    -0.24
    .modules
    -0.24
     Trades
    -0.23
     CES
    -0.22
    rowData
    -0.22
     isl
    -0.22
     //~
    -0.22
    BitFields
    -0.22
    POSITIVE LOGITS
     browser
    0.44
     bookmark
    0.43
    æµıè§ĪåĻ¨
    0.40
     navigator
    0.39
     bookmarks
    0.38
     navig
    0.36
     naveg
    0.36
     browsers
    0.35
    browser
    0.35
    bookmark
    0.35
    Activations Density 0.129%

    No Known Activations