© 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. 3104
    Prev
    Next
    INDEX
    Explanations

    targeted interventions

    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
    yards
    -0.24
    деÑģÑı
    -0.22
    maker
    -0.22
    site
    -0.22
    åŀ£
    -0.21
    sans
    -0.21
    bound
    -0.21
    space
    -0.21
    sed
    -0.21
    asso
    -0.21
    POSITIVE LOGITS
    adamente
    0.25
    ALLY
    0.22
    lement
    0.21
    edly
    0.21
     McN
    0.20
    äºİæѤ
    0.19
    æĢ§å¼º
    0.19
    ÑģÑı
    0.19
    gle
    0.19
     jew
    0.19
    Activations Density 0.015%

    No Known Activations