© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 17222
    Prev
    Next
    INDEX
    Explanations

    losing my mind or going crazy

    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
    Negative Logits
    éĢīæĭ
    -0.20
    лиÑĨ
    -0.18
    éĿĽ
    -0.18
    mmo
    -0.18
     extr
    -0.18
    mono
    -0.18
     fucked
    -0.18
    æĴº
    -0.17
    æĿĥå¨ģ
    -0.17
    lut
    -0.17
    POSITIVE LOGITS
    ï¼Īç¬ij
    0.24
    æ±Ĺ
    0.21
    åĩºæ±Ĺ
    0.20
    èł¹
    0.19
    åijµ
    0.19
    åı¯è°ĵ
    0.18
    èĪ¬çļĦ
    0.18
    åijµåijµ
    0.18
    åĺİ
    0.18
    åĵĪåĵĪ
    0.18
    Activations Density 0.428%

    No Known Activations