© 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. 507
    Prev
    Next
    INDEX
    Explanations

    various amounts or percentages

    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
     neither
    -0.29
    SION
    -0.28
    çIJĨ解åĴĮ
    -0.24
     Ones
    -0.23
    åĴĮæĶ¯æĮģ
    -0.22
     variables
    -0.22
     fundamentals
    -0.21
     viewBox
    -0.21
    .Invoke
    -0.21
     Dist
    -0.21
    POSITIVE LOGITS
    phans
    0.31
    usc
    0.25
    å»ĵ
    0.24
    é«ĺåĩº
    0.23
    similar
    0.23
    atl
    0.23
    ecom
    0.22
    æ·¤
    0.22
    erk
    0.22
    çłĴ
    0.21
    Activations Density 0.053%

    No Known Activations