© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15343
    Prev
    Next
    INDEX
    Explanations

    Iraq discussions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    æħĭ
    -0.17
    æľīæľŁ
    -0.17
    eds
    -0.15
    ighborhood
    -0.15
    ered
    -0.15
    ously
    -0.15
    eki
    -0.15
    ä¸ºæľŁ
    -0.15
    lider
    -0.14
    ackle
    -0.14
    POSITIVE LOGITS
     Kurdistan
    0.22
    ution
    0.18
    iness
    0.18
    time
    0.17
    ted
    0.17
    istan
    0.17
    lets
    0.16
    tran
    0.16
    ify
    0.16
    unch
    0.16
    Activations Density 0.011%

    No Known Activations