© 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. 12360
    Prev
    Next
    INDEX
    Explanations

    you followed by modal verbs

    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
     derp
    -0.23
    éĥĬ
    -0.20
    æīĵæĭ¼
    -0.20
    å¸Ĥåİ¿
    -0.19
    山寨
    -0.19
     gangbang
    -0.19
     деÑıÑĤелÑĮноÑģÑĤи
    -0.19
     cumshot
    -0.18
    ç³ĸå°¿
    -0.18
    èįīåĿª
    -0.18
    POSITIVE LOGITS
     ÐIJлекÑģан
    0.23
    arat
    0.22
    ä¸įè¦ģ
    0.21
    ÑĩÑĢежден
    0.21
     kind
    0.20
    agh
    0.20
    ä¸įè¡Į
    0.20
    说æĪij
    0.20
     guys
    0.19
     diff
    0.19
    Activations Density 0.027%

    No Known Activations