© 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. 2314
    Prev
    Next
    INDEX
    Explanations

    creating things

    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
    æľĢåIJİä¸Ģ次
    -0.27
     Newly
    -0.26
    IfExists
    -0.26
    éĹ·
    -0.25
     ÑĥÑģÑĤановлен
    -0.24
    auc
    -0.24
     being
    -0.24
     ostat
    -0.23
     freshly
    -0.23
     newly
    -0.22
    POSITIVE LOGITS
     anew
    0.39
    æĸ°çļĦ
    0.34
    åĴĮå®ĮåĸĦ
    0.33
    éĢĤåIJĪèĩªå·±
    0.31
    çļĦè¿ĩç¨ĭ
    0.30
    ä¸Ģ个æĸ°çļĦ
    0.30
    çļĦè¿ĩç¨ĭä¸Ń
    0.29
     ourselves
    0.29
     usable
    0.28
     enclave
    0.28
    Activations Density 0.709%

    No Known Activations