© 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. 1331
    Prev
    Next
    INDEX
    Explanations

    card game

    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
    roof
    -0.29
    Declared
    -0.24
    itud
    -0.24
     growth
    -0.23
    æıĨ
    -0.23
    ÑĢез
    -0.23
     пÑĢогноз
    -0.23
    ITED
    -0.22
    éĴ½
    -0.22
    çĶŁéķ¿
    -0.22
    POSITIVE LOGITS
     cards
    0.49
    åį¡çīĩ
    0.43
    /cards
    0.41
     Cards
    0.38
    cards
    0.38
     card
    0.37
    (cards
    0.36
     decks
    0.35
    èĹı
    0.34
    /card
    0.33
    Activations Density 0.027%

    No Known Activations