© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 515
    Prev
    Next
    INDEX
    Explanations

    eyebrows and eyelashes

    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
    éĢļè¡Įè¯ģ
    -0.23
     crib
    -0.22
     Yad
    -0.22
    ween
    -0.21
    åŁł
    -0.21
     nowrap
    -0.21
    -risk
    -0.21
     ÑĥÑģл
    -0.21
    .jd
    -0.20
    åħ¨æĸĩ
    -0.20
    POSITIVE LOGITS
     hairs
    0.30
    Hair
    0.28
     hair
    0.26
     Hair
    0.26
    hair
    0.26
    ç¿ł
    0.25
    abic
    0.25
    umen
    0.25
     fle
    0.23
    头åıij
    0.23
    Activations Density 0.004%

    No Known Activations