© 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. 2119
    Prev
    Next
    INDEX
    Explanations

    focusing on text preview

    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
    èĢģ大
    -0.24
    -Mart
    -0.23
    vinc
    -0.23
    (parcel
    -0.22
    æīĢ说çļĦ
    -0.22
    _nth
    -0.22
    STE
    -0.21
    declspec
    -0.21
    ä¹°çļĦ
    -0.21
    顺便
    -0.21
    POSITIVE LOGITS
     viewport
    0.30
     Viewing
    0.29
     fullscreen
    0.28
     text
    0.27
     Charset
    0.27
     viewing
    0.27
    æĸĩæľ¬
    0.27
    æŃ£æĸĩ
    0.26
     gloss
    0.26
     canvas
    0.26
    Activations Density 0.003%

    No Known Activations