© 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. 16629
    Prev
    Next
    INDEX
    Explanations

    violence or injury

    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
    æ°Ķæģ¯
    -0.25
    åijµ
    -0.22
    æIJĵ
    -0.21
    çļĦæ°Ķæģ¯
    -0.20
    /feed
    -0.20
    åįķè°ĥ
    -0.19
    å¢ŀè¿Ľ
    -0.19
    æħij
    -0.19
    æīŃ
    -0.19
    ifications
    -0.19
    POSITIVE LOGITS
    侧éĿ¢
    0.24
    è¦ģ害
    0.24
    èĩ´åij½
    0.23
    éĥ¨ä½į
    0.21
    èħ°éĥ¨
    0.20
    èī½
    0.19
    åľŁåľ°
    0.18
    çĸijä¼¼
    0.18
    çļĦåľŁåľ°
    0.18
    èħ¿éĥ¨
    0.18
    Activations Density 0.012%

    No Known Activations