© 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. 15832
    Prev
    Next
    INDEX
    Explanations

    parsing json or file data

    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
    亲
    -0.21
    éªł
    -0.20
    éľĨ
    -0.19
    éĢģè¾¾
    -0.19
    ilyn
    -0.19
     Tenn
    -0.18
    éľĩæħij
    -0.18
    å½ĵä¹ĭ
    -0.18
    _LL
    -0.18
    inium
    -0.17
    POSITIVE LOGITS
     parsing
    0.28
    è¿ĽæĿ¥
    0.27
    解读
    0.27
    解æŀIJ
    0.27
    FromString
    0.27
    .parse
    0.26
    读
    0.26
    æıIJçĤ¼
    0.25
    OrCreate
    0.25
    _Parse
    0.24
    Activations Density 0.376%

    No Known Activations