© 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. 3076
    Prev
    Next
    INDEX
    Explanations

    minus, subtract, subtraction

    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
    mans
    -0.22
    ular
    -0.19
    antage
    -0.19
    there
    -0.19
     verge
    -0.18
    kins
    -0.18
    anner
    -0.18
    ervers
    -0.18
    geh
    -0.18
    uc
    -0.17
    POSITIVE LOGITS
    æİīäºĨ
    0.26
    æİī
    0.23
    0.22
    webkit
    0.21
    -cost
    0.20
    .TryParse
    0.20
     hẳn
    0.19
    acro
    0.19
    æļĦ
    0.19
    زاÙĦ
    0.19
    Activations Density 0.011%

    No Known Activations