© 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. 2237
    Prev
    Next
    INDEX
    Explanations

    office document formats

    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
     Patreon
    -0.26
     Dop
    -0.25
    çĶ·ç¥ŀ
    -0.25
     Instagram
    -0.23
     tubing
    -0.23
    便åĪ©åºĹ
    -0.23
     psy
    -0.23
     Theta
    -0.23
     Piper
    -0.23
     FBI
    -0.23
    POSITIVE LOGITS
    Formats
    0.30
    formats
    0.27
     mimetype
    0.27
    çļĤ
    0.26
    airo
    0.24
    office
    0.24
    åĬŀåħ¬
    0.24
     retiring
    0.24
    è´¢æĶ¿
    0.24
    -office
    0.23
    Activations Density 0.041%

    No Known Activations