© 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. 15011
    Prev
    Next
    INDEX
    Explanations

    disastrous, catastrophic events

    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
    ì¦Ŀ
    -0.19
    usal
    -0.18
    orc
    -0.18
    èµĦæĸĻæĺ¾ç¤º
    -0.17
     лиÑĨа
    -0.17
    åľ°åĮºçļĦ
    -0.17
    åıĹè´¿
    -0.17
    è¾ĥ强
    -0.16
     ÐĴеÑĢ
    -0.16
    istra
    -0.16
    POSITIVE LOGITS
    ous
    0.26
    Occurred
    0.22
    æĢ§çļĦ
    0.21
    ä¹İ
    0.21
    è¹ĭ
    0.20
    ful
    0.20
    ry
    0.19
    _OCCURRED
    0.18
    OUS
    0.18
    æĿ¥ä¸´
    0.18
    Activations Density 0.013%

    No Known Activations