© 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. 13926
    Prev
    Next
    INDEX
    Explanations

    groundwater contamination and discharge

    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
    âĸ¹
    -0.23
    éĤ®è½®
    -0.20
    糸
    -0.20
    éĢłèĪ¹
    -0.19
    brig
    -0.19
    æĶ¶æĭ¾
    -0.19
    çħ½
    -0.19
    imizer
    -0.19
     Minority
    -0.18
    mPid
    -0.18
    POSITIVE LOGITS
    åľ°ä¸ĭæ°´
    0.30
    æ·±å±Ĥ
    0.29
    æ°´æºIJ
    0.26
     groundwater
    0.25
    èĻij
    0.24
     recharge
    0.24
    åľ°ä¸ĭ
    0.23
     underground
    0.23
     tunnels
    0.22
    çĽijæµĭ
    0.22
    Activations Density 0.023%

    No Known Activations