© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10635
    Prev
    Next
    INDEX
    Explanations

    information, facts, evidence, risk, child, food

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    æľ
    -0.21
    ÙĬØ©
    -0.19
    çī¹æ®ĬæĥħåĨµ
    -0.17
    Ä°N
    -0.16
    èĮĦ
    -0.16
    inus
    -0.16
    âŃIJ
    -0.16
    ination
    -0.16
    uptools
    -0.16
    æĸ¹éĿ¢çļĦ
    -0.16
    POSITIVE LOGITS
    æ®Ĩ
    0.21
    oco
    0.20
    ymm
    0.18
     Reaper
    0.17
    wald
    0.16
    htub
    0.16
    .communication
    0.16
    sent
    0.16
    åıĹ
    0.16
    sert
    0.15
    Activations Density 0.620%

    No Known Activations