© 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. 1460
    Prev
    Next
    INDEX
    Explanations

    invention relates

    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
    alu
    -0.25
    оÑĩно
    -0.24
     воÑģ
    -0.23
    TestData
    -0.23
     originals
    -0.23
    vac
    -0.23
     etiqu
    -0.22
     famously
    -0.21
     tagName
    -0.21
     lids
    -0.21
    POSITIVE LOGITS
     herein
    0.30
    æĹ¨åľ¨
    0.27
    åľ¨è¿Ļæĸ¹éĿ¢
    0.26
    ç«ĭ足
    0.25
    æīĢåľ¨åľ°
    0.25
    æľ¬çĿĢ
    0.23
    æŨ
    0.23
    here
    0.23
    å§ĭç»ĪåĿļæĮģ
    0.23
     intend
    0.23
    Activations Density 0.437%

    No Known Activations