© 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. 2081
    Prev
    Next
    INDEX
    Explanations

    curtain or Curtis

    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
    ../../../
    -0.27
    çĦ¶æĺ¯
    -0.24
    ert
    -0.23
    ent
    -0.23
    cing
    -0.23
    วย
    -0.22
     <![
    -0.20
    otted
    -0.20
    ery
    -0.20
    itives
    -0.20
    POSITIVE LOGITS
    ãģĵãģ¨
    0.25
     sheer
    0.22
    ailing
    0.19
     hitch
    0.19
    sole
    0.19
    ä¹ĭ举
    0.18
    shade
    0.18
    !--
    0.17
    FlowLayout
    0.17
    ned
    0.17
    Activations Density 0.008%

    No Known Activations