© 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. 3088
    Prev
    Next
    INDEX
    Explanations

    on-base percentage

    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
    Not in Any Lists

    No Comments

    Negative Logits
    rozen
    -0.27
    oden
    -0.22
     standoff
    -0.21
    绣
    -0.21
    ä»»ä½ķä¸Ģ个
    -0.21
    æµij
    -0.21
    until
    -0.21
    []↵
    -0.21
     CONDITIONS
    -0.20
    åħ¬åħ±èµĦæºIJ
    -0.20
    POSITIVE LOGITS
    /power
    0.24
    羡
    0.23
     ratio
    0.23
    人家
    0.23
    å¼ĤæĢ§
    0.22
    istan
    0.22
    çĮĹ
    0.22
    indle
    0.21
    ifier
    0.21
    esen
    0.21
    Activations Density 0.001%

    No Known Activations