© 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. 2173
    Prev
    Next
    INDEX
    Explanations

    fiber/fabric/material types

    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
     barric
    -0.27
    çģŃçģ«
    -0.25
     altar
    -0.24
     Mushroom
    -0.24
    minecraft
    -0.24
     tomb
    -0.24
     Minecraft
    -0.24
     поÑĢÑĤал
    -0.24
    ä¸ŃåĽ½æ±½è½¦
    -0.24
     asteroid
    -0.24
    POSITIVE LOGITS
    纤维
    0.38
     fibers
    0.38
     fiber
    0.37
    éĿ¢æĸĻ
    0.36
     cotton
    0.35
     linen
    0.34
    纺
    0.34
     textile
    0.33
    纱
    0.33
    fiber
    0.32
    Activations Density 0.020%

    No Known Activations