© 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. 14129
    Prev
    Next
    INDEX
    Explanations

    games and sets scores

    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
    被åĬ¨
    -0.18
     Walters
    -0.18
    akens
    -0.17
    èĦĤ
    -0.17
    ä¸ĭ游
    -0.17
     marshaller
    -0.17
    ancock
    -0.17
     Gros
    -0.16
    abric
    -0.16
     deco
    -0.16
    POSITIVE LOGITS
    çĪ¬
    0.23
    çĶŁæŃ»
    0.20
    idUser
    0.20
    ç²¾ç¥ŀæĸĩæĺİ
    0.20
    plets
    0.20
    俨
    0.19
    nings
    0.19
    çIJµ
    0.19
    encies
    0.19
    çĪ¬ä¸Ĭ
    0.19
    Activations Density 0.010%

    No Known Activations