© 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. 542
    Prev
    Next
    INDEX
    Explanations

    Council followed by specific organizations

    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
    ãģĵãģ¨
    -0.20
    edom
    -0.18
    ending
    -0.18
    ãģĦãĤĭ
    -0.18
    per
    -0.18
    throw
    -0.17
     sort
    -0.17
     há
    -0.17
    -ever
    -0.17
    ÙĥÙĨ
    -0.17
    POSITIVE LOGITS
    wide
    0.28
    主å¸Ń
    0.27
    naire
    0.24
    mates
    0.24
    ors
    0.23
    naires
    0.22
    ize
    0.22
    hip
    0.22
    rooms
    0.22
    -wide
    0.21
    Activations Density 0.016%

    No Known Activations