© 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. 14886
    Prev
    Next
    INDEX
    Explanations

    posted, updated, open, settings

    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
    ly
    -0.27
    ÑģÑı
    -0.22
    ed
    -0.19
    lyn
    -0.19
    \n
    -0.18
    sek
    -0.18
    ||
    -0.17
    ¹
    -0.17
    ÙĩÙħ
    -0.17
    ally
    -0.17
    POSITIVE LOGITS
    ãģĹãģ¾ãģĨ
    0.21
    entifier
    0.20
    olated
    0.19
    æīĭåĬ¿
    0.19
    RITE
    0.17
    phans
    0.17
    åŃIJéĩĮ
    0.17
    éĢŁåº¦å¿«
    0.17
    unami
    0.17
    ð¬ĮĹ
    0.16
    Activations Density 0.076%

    No Known Activations