© 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. 1753
    Prev
    Next
    INDEX
    Explanations

    surface

    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
    äºĽä»Ģä¹Ī
    -0.22
    ../../../
    -0.21
    çĦ¶æĺ¯
    -0.21
     purse
    -0.20
    éĿ¢åŃIJ
    -0.20
    注åĨĮèµĦæľ¬
    -0.19
    ä¸Ĭå²Ĺ
    -0.19
    æł·çļĦ
    -0.19
    ysis
    -0.19
    ssize
    -0.19
    POSITIVE LOGITS
    less
    0.26
    ted
    0.25
    ware
    0.22
    ulent
    0.22
    -level
    0.21
    ral
    0.21
    é¢Ĭ
    0.21
    cake
    0.20
    e
    0.20
    /head
    0.19
    Activations Density 0.041%

    No Known Activations