© 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. 12221
    Prev
    Next
    INDEX
    Explanations

    `.inflate`, `.Description`, `.js`, `.innerHTML`, `.setLevel`

    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
    colm
    -0.19
    ãģĦãģĨ
    -0.19
    ç½ijé¦ĸ页
    -0.18
    主è§Ĥ
    -0.18
    åĪĻæĺ¯
    -0.17
    æĤ¨çļĦåŃ©åŃIJ
    -0.17
    éĴµ
    -0.16
    è¨ĢãģĨ
    -0.16
    æ´ĹèĦ¸
    -0.16
    æĹĥ
    -0.16
    POSITIVE LOGITS
    çIJĨ
    0.18
     помоÑīи
    0.17
     jun
    0.17
    ï¸
    0.16
     ime
    0.16
    _cre
    0.15
    骨
    0.15
    é¼ĵèĪŀ
    0.15
     pearl
    0.15
    åIJİ
    0.14
    Activations Density 0.712%

    No Known Activations