© 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. 12005
    Prev
    Next
    INDEX
    Explanations

    violent protests and riots

    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
    arb
    -0.20
    æ³ķè§Ħ
    -0.19
     confer
    -0.18
    èĤºçĻĮ
    -0.18
    éĤª
    -0.18
    èijĹä½ľ
    -0.18
    comma
    -0.18
    çĸijéļ¾
    -0.18
     everlasting
    -0.18
    æľ¯è¯Ń
    -0.17
    POSITIVE LOGITS
    èĶĵ延
    0.26
    æŃĩ
    0.23
    æĭīå¼Ģ
    0.21
    æĦĪ
    0.21
    anye
    0.21
    æİ¥è¿ŀ
    0.21
    è°©
    0.20
    _HELPER
    0.20
    åİŁæĿIJæĸĻ
    0.20
     riots
    0.20
    Activations Density 0.018%

    No Known Activations