© 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. 3178
    Prev
    Next
    INDEX
    Explanations

    osmotic

    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
    .TryParse
    -0.25
    æŀŃ
    -0.24
    空ä¸Ń
    -0.24
     buried
    -0.24
     cresc
    -0.22
     spur
    -0.22
     ghế
    -0.21
    urve
    -0.21
     gramm
    -0.20
    åIJ¸çĥŁ
    -0.20
    POSITIVE LOGITS
    flow
    0.23
    å±ıéļľ
    0.22
    gent
    0.22
    积æ·Ģ
    0.22
     Bradley
    0.22
    >Add
    0.21
    åħij
    0.21
     Hog
    0.21
     perme
    0.21
    kle
    0.21
    Activations Density 0.049%

    No Known Activations