© 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. 11487
    Prev
    Next
    INDEX
    Explanations

    disease management and control

    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
    寥
    -0.23
    è¿ŀ
    -0.22
    connector
    -0.21
    éĻ·åħ¥
    -0.21
    ovolta
    -0.21
    xee
    -0.21
    为æ°ij
    -0.21
    åIJĪæ³ķæĢ§
    -0.20
    çĦĬ
    -0.20
    enco
    -0.20
    POSITIVE LOGITS
    管çIJĨ
    0.31
    管çIJĨåĴĮ
    0.31
     management
    0.31
     manage
    0.30
    çĽijæµĭ
    0.28
    è¾¾æłĩ
    0.27
    稳å®ļ
    0.27
     managing
    0.27
    -management
    0.26
    管çIJĨä¸Ńå¿ĥ
    0.25
    Activations Density 0.244%

    No Known Activations