© 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. 15178
    Prev
    Next
    INDEX
    Explanations

    computer parts and specs

    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
     trùng
    -0.23
    amarin
    -0.22
    /WebAPI
    -0.21
    YW
    -0.20
    pyx
    -0.20
    çł£
    -0.20
    YRO
    -0.20
    tractor
    -0.20
    Leod
    -0.19
    æĸĩæ¡Ī
    -0.19
    POSITIVE LOGITS
    硬件
    0.28
    éħįç½®
    0.27
    æĢ§ä»·æ¯Ķ
    0.27
    ç¬Ķè®°æľ¬
    0.27
    çĶµèĦij
    0.27
    _CPU
    0.26
    æķ£çĥŃ
    0.25
    ç»Ħè£ħ
    0.25
    æIJŃéħį
    0.24
    å½ĵä»Ĭ
    0.24
    Activations Density 0.058%

    No Known Activations