© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15209
    Prev
    Next
    INDEX
    Explanations

    online classifieds and chat

    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
    azo
    -0.21
    é©»æĿij
    -0.20
    upy
    -0.19
    æ¬Ĭ
    -0.19
    ä½ĵéĩı
    -0.19
    olk
    -0.19
    çĽĺçĤ¹
    -0.19
    æĿĥ
    -0.18
    .priority
    -0.18
    aticon
    -0.18
    POSITIVE LOGITS
    åľ¨çº¿
    0.31
     online
    0.29
     anonymity
    0.28
    internet
    0.28
     internet
    0.26
     Internet
    0.26
    åľ¨ç½ijä¸Ĭ
    0.26
    天涯
    0.25
    äºĴèģĶç½ij
    0.24
     Online
    0.24
    Activations Density 0.041%

    No Known Activations