© 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. 1791
    Prev
    Next
    INDEX
    Explanations

    biblical prophecies and predictions

    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
    é©»æĿij
    -0.25
     môi
    -0.25
    èĦĤ
    -0.23
    ieee
    -0.23
     Negot
    -0.23
    GRAM
    -0.23
    å¤ĦåĪĨ
    -0.22
    GOP
    -0.22
     negotiation
    -0.22
     Peer
    -0.21
    POSITIVE LOGITS
     legacy
    0.30
     precedent
    0.29
    legacy
    0.29
     predictive
    0.27
     Legacy
    0.26
    Legacy
    0.25
     proph
    0.25
     predictions
    0.25
     fulfilled
    0.25
     Jewish
    0.25
    Activations Density 0.017%

    No Known Activations