© 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. 561
    Prev
    Next
    INDEX
    Explanations

    New York

    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
    OfSize
    -0.21
    æĸ°åĵģ
    -0.20
    èī°è¾Ľ
    -0.20
    CurrentUser
    -0.19
    åĢij
    -0.19
     NOI
    -0.19
     newer
    -0.19
     newcomers
    -0.19
     newsletter
    -0.19
     newcomer
    -0.19
    POSITIVE LOGITS
    -born
    0.33
    bies
    0.30
    born
    0.30
    foundland
    0.29
     Zealand
    0.28
     york
    0.27
    ness
    0.27
    swire
    0.27
    bie
    0.26
    -generation
    0.25
    Activations Density 0.169%

    No Known Activations