© 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. 16408
    Prev
    Next
    INDEX
    Explanations

    measuring tools and devices

    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
    éľĪ
    -0.18
    pé
    -0.18
    isoft
    -0.18
    ALAR
    -0.18
    quil
    -0.18
    åİĨåı²æĸ°
    -0.18
    .openConnection
    -0.17
    æĵİ
    -0.17
    озд
    -0.17
    orate
    -0.17
    POSITIVE LOGITS
    å°º
    0.35
     measuring
    0.31
    æµĭéĩı
    0.31
    å·¥åħ·
    0.29
     scale
    0.25
    æĺ¯çĶ¨æĿ¥
    0.25
    åŁºåĩĨ
    0.25
     measurement
    0.25
    仪
    0.25
    尺度
    0.25
    Activations Density 0.042%

    No Known Activations