© 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. 16835
    Prev
    Next
    INDEX
    Explanations

    health monitoring and tracking

    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
    urniture
    -0.21
    åħ¨é¢Ŀ
    -0.20
    -pagination
    -0.20
    èĪIJ
    -0.20
    éĽİ
    -0.19
    ationale
    -0.19
    afil
    -0.19
    çī¹æ®ĬæĥħåĨµ
    -0.19
    Tier
    -0.18
    TEX
    -0.18
    POSITIVE LOGITS
    è®°å½ķ
    0.32
    çĽijæµĭ
    0.29
     record
    0.26
    åģ¥èº«
    0.25
     tracking
    0.25
    è¨ĺéĮĦ
    0.25
    è·Łè¸ª
    0.25
     recorder
    0.25
     records
    0.24
     monitor
    0.24
    Activations Density 0.042%

    No Known Activations