© 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. 15070
    Prev
    Next
    INDEX
    Explanations

    criminal charges

    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
     widow
    -0.21
     gol
    -0.20
     polar
    -0.19
     rej
    -0.18
     Apocalypse
    -0.18
    åıįè¿ĩæĿ¥
    -0.18
     meg
    -0.18
    西è£ħ
    -0.18
    åĩºåĽ½
    -0.18
    è¥ģ
    -0.18
    POSITIVE LOGITS
    ä»»ä½ķ人
    0.24
    å½ĵæĻļ
    0.22
    çł´éŨ
    0.22
    使人
    0.21
    æĹłå£°
    0.21
    è¿Ŀæ³ķè¡Į为
    0.21
    该åİ¿
    0.21
    该éĻ¢
    0.20
    ligt
    0.20
    Ñįм
    0.20
    Activations Density 0.035%

    No Known Activations