© 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. 16358
    Prev
    Next
    INDEX
    Explanations

    Chinese characters

    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
    -m
    -0.20
    仲
    -0.19
    affen
    -0.19
    ‘
    -0.18
    交
    -0.18
    çµ®
    -0.18
    “
    -0.18
     Ñ
    -0.18
    âĢ¦
    -0.17
    âĢŀ
    -0.17
    POSITIVE LOGITS
    è´±
    0.22
    楮
    0.21
    çĶij
    0.20
    éĵĭ
    0.20
    毳
    0.20
    ç»ĿæľĽ
    0.20
    é³³
    0.19
    夸大
    0.19
    ä¸įç®¡ä½ł
    0.19
    é¾Ī
    0.18
    Activations Density 0.813%

    No Known Activations