© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3197
    Prev
    Next
    INDEX
    Explanations

    `#include` followed by `<`

    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
    Negative Logits
    enums
    -0.23
    对å¤ĸå¼ĢæĶ¾
    -0.23
    _exit
    -0.23
    opened
    -0.22
    æĴ¤
    -0.22
    å¼ĢæĶ¾
    -0.22
     createState
    -0.22
    å¼ĢéŨ
    -0.21
    ificate
    -0.21
    reopen
    -0.21
    POSITIVE LOGITS
    vore
    0.25
    GRID
    0.23
    OTP
    0.22
     dar
    0.22
    éĤĬ
    0.22
    owy
    0.22
    å¦ĤæŀľæĤ¨
    0.21
     Legion
    0.21
     immac
    0.21
    /original
    0.20
    Activations Density 0.001%

    No Known Activations