© 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. 1887
    Prev
    Next
    INDEX
    Explanations

    guides, informs, or helps decisions

    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
    æĸĩåĮĸ
    -0.26
    ett
    -0.25
     Err
    -0.22
    çĤ¹åĩ»æŁ¥çľĭ
    -0.22
    coe
    -0.22
     lá
    -0.22
    GR
    -0.22
    赶ä¸Ĭ
    -0.21
     cultural
    -0.21
    .office
    -0.21
    POSITIVE LOGITS
     later
    0.32
    ä¸ĭä¸ĢæŃ¥
    0.32
    åIJİç»Ń
    0.32
     subsequent
    0.31
    later
    0.30
    æĹ¥åIJİ
    0.30
     basis
    0.29
     determining
    0.29
     Later
    0.28
    åIJİéĿ¢çļĦ
    0.28
    Activations Density 0.162%

    No Known Activations