© 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. 17035
    Prev
    Next
    INDEX
    Explanations

    indoor facilities

    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
    ofile
    -0.20
    _SITE
    -0.19
     Ñĩа
    -0.19
    ä¸ĢæĬĬ
    -0.19
    çĤ¹å¤ļ
    -0.19
     Fence
    -0.19
    sites
    -0.18
    jt
    -0.18
    éĴ¿
    -0.18
    bole
    -0.18
    POSITIVE LOGITS
    室åĨħ
    0.47
     indoor
    0.38
     indoors
    0.35
    室
    0.33
     floor
    0.31
     Indoor
    0.31
    floor
    0.28
     Floor
    0.27
    .floor
    0.26
    åľ°æĿ¿
    0.26
    Activations Density 0.034%

    No Known Activations