© 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. 15952
    Prev
    Next
    INDEX
    Explanations

    descriptive characteristics

    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
    âīĤ
    -0.43
    ⧫
    -0.33
    Ǧ
    -0.32
    âĨĽ
    -0.32
    â¯
    -0.31
    á´¼
    -0.30
    ÈĴ
    -0.30
    ḧ
    -0.30
    	RTLR
    -0.30
    ⣷
    -0.30
    POSITIVE LOGITS
    çī¹å¾ģ
    0.37
    çī¹çĤ¹æĺ¯
    0.29
    è¦ĭãģŁ
    0.27
    å½¢çĬ¶
    0.26
     characteristic
    0.25
    ãĥģãĥ¥
    0.25
    ãĥĩãĤ¶ãĤ¤ãĥ³
    0.24
    trait
    0.24
    çī¹çĤ¹
    0.24
    ç½ijç«Ļ建设
    0.24
    Activations Density 0.216%

    No Known Activations