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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 101
    Prev
    Next
    INDEX
    Explanations

    slugging percentage or stale Danish/style

    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
    inya
    -0.21
     возможноÑģÑĤи
    -0.19
     Magical
    -0.19
     flagged
    -0.19
     Gentle
    -0.18
     Penal
    -0.18
    ÙħÙĥÙĨ
    -0.18
     plea
    -0.18
    -educated
    -0.18
     alleged
    -0.18
    POSITIVE LOGITS
    ll
    0.26
    kre
    0.25
    fest
    0.25
    athon
    0.24
    esses
    0.23
    mates
    0.23
    fish
    0.23
    book
    0.23
    ger
    0.23
    ess
    0.22
    Activations Density 0.004%

    No Known Activations