© 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. 10889
    Prev
    Next
    INDEX
    Explanations

    past or ago

    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
    åĤ¥
    -0.20
    æĴ©
    -0.19
    æ¯ĵ
    -0.19
    é©Ń
    -0.19
    éĨĴ缮
    -0.19
    later
    -0.18
    Crypto
    -0.18
    åı¦
    -0.18
    odesk
    -0.18
    оÑī
    -0.18
    POSITIVE LOGITS
    (before
    0.24
    ä»ħä»ħæĺ¯
    0.21
    ãģłãģ¨
    0.21
    èĭij
    0.20
    èĢĮçİ°åľ¨
    0.20
    缸æ¯Ķä¹ĭä¸ĭ
    0.19
    çĶŁæ´»
    0.19
     intact
    0.19
    就已ç»ı
    0.19
     useRouter
    0.18
    Activations Density 0.101%

    No Known Activations