© 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. 3286
    Prev
    Next
    INDEX
    Explanations

    trailing behind, down

    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
    åºĨåħ¸
    -0.24
    导
    -0.24
    prise
    -0.23
    çĸ¹
    -0.22
    ä¸ĵ
    -0.22
    å¥ĸ
    -0.21
     despre
    -0.21
    ä¼ł
    -0.21
    .locals
    -0.20
    hey
    -0.20
    POSITIVE LOGITS
    å½¢åĬ¿
    0.24
     reversed
    0.22
    /up
    0.21
    å±ĢéĿ¢
    0.21
    egas
    0.21
    auge
    0.21
     Belly
    0.21
    è¡¥åģ¿
    0.21
     glossy
    0.21
     avis
    0.21
    Activations Density 0.008%

    No Known Activations