© 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. 3068
    Prev
    Next
    INDEX
    Explanations

    suite of

    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
    neath
    -0.23
    hausen
    -0.23
    nt
    -0.20
    ä»Ģä¹Īåij¢
    -0.20
    hoff
    -0.20
    nya
    -0.20
     تعاÙĦÙī
    -0.19
    izedName
    -0.19
    sono
    -0.19
     ÑģлÑĥÑĩаÑı
    -0.19
    POSITIVE LOGITS
    åĨħçļĦ
    0.25
    iou
    0.22
    ernel
    0.22
    iens
    0.21
    lets
    0.21
    åı¸ä»¤
    0.20
    atic
    0.20
    ä¸ŃåIJ«æľī
    0.20
    une
    0.20
    tlement
    0.19
    Activations Density 0.016%

    No Known Activations