© 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. 1759
    Prev
    Next
    INDEX
    Explanations

    create or solve

    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
     dine
    -0.23
    客æĪ·çļĦ
    -0.23
    unbind
    -0.23
    è¶ĭäºİ
    -0.22
     resent
    -0.22
    -archive
    -0.22
     Liv
    -0.22
     liv
    -0.22
    åıĤä¸İ
    -0.22
    èį¤
    -0.22
    POSITIVE LOGITS
    ä¸įåĪĨ
    0.28
    ç»ĵæŀľ
    0.26
    startup
    0.25
    å¦ĤæľŁ
    0.25
    getResult
    0.24
    確ãģĭ
    0.24
    åĸĩåıŃ
    0.23
     malformed
    0.23
    è¾¹çķĮ
    0.23
    yield
    0.22
    Activations Density 0.006%

    No Known Activations