© 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. 3033
    Prev
    Next
    INDEX
    Explanations

    copyright and license

    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
    -related
    -0.26
    atically
    -0.25
    ande
    -0.23
    ier
    -0.23
    ular
    -0.23
    ette
    -0.23
    —even
    -0.23
    Knight
    -0.21
    [D
    -0.21
    andre
    -0.21
    POSITIVE LOGITS
    индив
    0.32
    медиÑĨинÑģк
    0.31
    пÑĢакÑĤик
    0.31
    индивид
    0.31
    ÑĩÑĢ
    0.29
    пÑĢоÑĦеÑģÑģионал
    0.28
    webkit
    0.28
    ÑĢеги
    0.27
    еÑģÑĤеÑģÑĤвенн
    0.27
    наÑĨионалÑĮн
    0.25
    Activations Density 0.619%

    No Known Activations