© 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. 2470
    Prev
    Next
    INDEX
    Explanations

    See the license

    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
     battle
    -0.28
     battles
    -0.23
     ware
    -0.21
    atomy
    -0.21
    ..
    -0.21
    est
    -0.21
     enc
    -0.21
    *.
    -0.21
     season
    -0.20
     relay
    -0.20
    POSITIVE LOGITS
     zwar
    0.33
     However
    0.30
    åľ¨éĤ£éĩĮ
    0.29
    è¿Ļåı¥è¯Ŀ
    0.27
    ãģĹãģĭãģĹ
    0.27
    åľ¨è¿Ļæĸ¹éĿ¢
    0.27
    åľ¨è¿Ļç§į
    0.26
    请注æĦı
    0.26
    为æѤ
    0.26
    åľ¨è¿ĻéĩĮ
    0.25
    Activations Density 0.314%

    No Known Activations