© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12959
    Prev
    Next
    INDEX
    Explanations

    power outages and blackouts

    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
    ater
    -0.23
    yard
    -0.20
    shots
    -0.18
    å´
    -0.18
    ä¸įéĶĻçļĦ
    -0.17
    æĮĿ
    -0.17
    tail
    -0.17
    nth
    -0.17
    -0.16
    nels
    -0.16
    POSITIVE LOGITS
    Occurred
    0.22
    èıĮ
    0.18
    /false
    0.18
    æĪĸå¤ļ
    0.18
     areas
    0.17
    æĿ¥ä¸´
    0.17
    _OCCURRED
    0.17
    ä¸Ģçīĩ
    0.17
    顾
    0.17
    enment
    0.17
    Activations Density 0.005%

    No Known Activations