© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1463
    Prev
    Next
    INDEX
    Explanations

    European and foreign connection

    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
     DEVICE
    -0.26
     Piper
    -0.25
     Toolbox
    -0.25
    rawer
    -0.23
    交æİ¥
    -0.23
     Segment
    -0.22
    _SELECTOR
    -0.22
    浯
    -0.21
    SENSOR
    -0.21
    >$
    -0.21
    POSITIVE LOGITS
    -like
    0.34
     European
    0.30
     like
    0.30
    like
    0.30
    欧洲
    0.27
     Europe
    0.26
     foreign
    0.25
     unlike
    0.25
     Like
    0.25
     akin
    0.25
    Activations Density 0.553%

    No Known Activations