© 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. 3318
    Prev
    Next
    INDEX
    Explanations

    identifying presence or existence

    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
    -schema
    -0.25
    è¯
    -0.23
     Lifetime
    -0.22
     fullscreen
    -0.22
     classifications
    -0.22
    è¯Ħ级
    -0.22
     vej
    -0.22
    éķľå¤´
    -0.22
     rightfully
    -0.22
    ä¸Ģ身
    -0.21
    POSITIVE LOGITS
    æıIJéĨĴ
    0.43
     presence
    0.36
     reminded
    0.34
     indication
    0.32
     remind
    0.32
     reminders
    0.32
    身份
    0.32
     identity
    0.31
     existence
    0.30
     indicating
    0.30
    Activations Density 0.309%

    No Known Activations