© 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. 16519
    Prev
    Next
    INDEX
    Explanations

    data changes

    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
    RIX
    -0.20
    éĿłè°±
    -0.19
    .basename
    -0.19
    æĿ¿æĿIJ
    -0.19
    大大æıIJé«ĺ
    -0.18
    åĿĬ
    -0.18
    森
    -0.18
    imum
    -0.18
    çĤ¹äºĨ
    -0.17
    гон
    -0.17
    POSITIVE LOGITS
    转移
    0.22
    æīĢæľī
    0.21
     Imported
    0.19
    çİ°æľī
    0.19
     transfers
    0.19
    åħ¨èĩªåĬ¨
    0.19
    æĮĤ
    0.18
     Instant
    0.18
    çĶŁæ¶¯
    0.18
     transfer
    0.18
    Activations Density 0.021%

    No Known Activations