© 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. 16070
    Prev
    Next
    INDEX
    Explanations

    activate `C`

    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
    éķ¿å¤§
    -0.23
    åĶ¯
    -0.23
    äºĨä¸ĢäºĽ
    -0.22
    ä½ĨçĶ±äºİ
    -0.22
    æŀģ大
    -0.21
     Bes
    -0.21
    åĽłåħ¶
    -0.20
    äºĨ个
    -0.20
    äºĨä¸Ģä¸ĭ
    -0.20
    åİĨæŶ
    -0.20
    POSITIVE LOGITS
     yourself
    0.38
    å°½åı¯èĥ½
    0.33
    å°½æĹ©
    0.31
    å°½éĩı
    0.31
     your
    0.30
    ä½łçļĦ
    0.29
    ä¸įè¦ģ
    0.29
    ä¸įè¦ģ太
    0.29
    对èĩªå·±çļĦ
    0.28
     Äijừng
    0.27
    Activations Density 0.103%

    No Known Activations