© 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. 1651
    Prev
    Next
    INDEX
    Explanations

    and, or, etc

    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
    åĪĩæĸŃ
    -0.23
    (tf
    -0.22
    Forecast
    -0.20
    (TR
    -0.20
     STATS
    -0.20
    æ¿Ģ
    -0.20
    Queue
    -0.20
     TIMESTAMP
    -0.20
    alin
    -0.20
    åĬ©éķ¿
    -0.20
    POSITIVE LOGITS
    åıĬ缸åħ³
    0.27
    æĪĸåħ¶ä»ĸ
    0.27
    æĪĸèĢħåħ¶ä»ĸ
    0.27
    åIJĦ个çݯèĬĤ
    0.27
    以åıĬåħ¶ä»ĸ
    0.26
     whatever
    0.25
     etc
    0.25
    åıĬåħ¶ä»ĸ
    0.24
    etc
    0.24
    åIJĦ个æĸ¹éĿ¢
    0.24
    Activations Density 0.206%

    No Known Activations