© 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. 11270
    Prev
    Next
    INDEX
    Explanations

    crashed or accident investigation

    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
    æµģåIJij
    -0.23
    çŁ³å¤´
    -0.21
    æ°ijæ£Ģå¯ŁéĻ¢
    -0.20
    æ·ĭ
    -0.19
    æĶ¾æīĭ
    -0.19
    åħ¥æĪ·
    -0.19
     locksmith
    -0.19
     Jail
    -0.18
    undy
    -0.18
    ĵåIJį
    -0.18
    POSITIVE LOGITS
    äºĭæķħ
    0.27
    çģ¾éļ¾
    0.26
    é£ŀæľº
    0.26
    åĿł
    0.25
    é£ŀè¡Įåijĺ
    0.25
    æľºç»Ħ
    0.25
    伤亡
    0.24
     fatal
    0.24
    é£ŀè¡Į
    0.24
    è¿IJè¾ĵ
    0.23
    Activations Density 0.041%

    No Known Activations