© 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. 2579
    Prev
    Next
    INDEX
    Explanations

    character names followed by 's

    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
    被认为
    -0.25
    缸åħ³çļĦ
    -0.24
     cle
    -0.24
    被认为æĺ¯
    -0.23
     integral
    -0.23
    ucle
    -0.23
    æľ¬ç½ijç«Ļ
    -0.23
     sinc
    -0.23
    licing
    -0.23
     topic
    -0.22
    POSITIVE LOGITS
    åijĬè¯ī她
    0.27
    TED
    0.26
    ç¦Ģ
    0.24
    DTV
    0.23
     TED
    0.23
     tarafından
    0.23
    -Men
    0.22
    æĮĩ导ä¸ĭ
    0.22
    åijĬè¯īä»ĸ
    0.22
     approve
    0.22
    Activations Density 0.051%

    No Known Activations