© 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. 2522
    Prev
    Next
    INDEX
    Explanations

    user input or interface

    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
    大家
    -0.26
    åľ£
    -0.26
    ä¸ŃåĽ½çī¹èī²
    -0.22
    orado
    -0.22
    ä¸įå½±åĵį
    -0.22
    æĥº
    -0.22
    çī¢åĽº
    -0.21
    erver
    -0.21
    atra
    -0.21
    幸
    -0.21
    POSITIVE LOGITS
     request
    0.27
    éĢģæĿ¥
    0.26
    request
    0.23
     Demp
    0.23
    请æ±Ĥ
    0.23
    -defined
    0.23
    æıIJåĩºçļĦ
    0.22
    æĪijçĪ±ä½ł
    0.22
    æıIJä¾ĽçļĦ
    0.22
     asking
    0.22
    Activations Density 0.054%

    No Known Activations