© 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. 11812
    Prev
    Next
    INDEX
    Explanations

    when indicated

    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
    ãģľ
    -0.20
    追究
    -0.20
    èµ°äºĨ
    -0.19
    è¶Ĭé«ĺ
    -0.19
    æīĢ以说
    -0.19
    è¶Ĭæĺ¯
    -0.18
    çĶŁæ´»æĸ¹å¼ı
    -0.18
    åİ»æī¾
    -0.18
    è¿ĺåĮħæĭ¬
    -0.18
    åıªä¼ļ
    -0.18
    POSITIVE LOGITS
    åIJĪéĢĤ
    0.29
    å¿ħè¦ģ
    0.29
    åIJĪéĢĤçļĦ
    0.27
     необÑħодимоÑģÑĤи
    0.26
     needed
    0.26
    éĢĤå®ľ
    0.26
    å¿ħè¦ģçļĦ
    0.25
    éľĢè¦ģ
    0.25
     necessary
    0.25
     íķĦìļĶ
    0.24
    Activations Density 0.085%

    No Known Activations