© 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. 15422
    Prev
    Next
    INDEX
    Explanations

    want to

    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
    akov
    -0.18
    jem
    -0.18
    werp
    -0.17
    çĶ
    -0.17
    æľªçŁ¥
    -0.17
    IALOG
    -0.17
    çĦī
    -0.17
    airy
    -0.17
     geme
    -0.17
    .ShouldBe
    -0.17
    POSITIVE LOGITS
    çļĦè¯Ŀ
    0.26
    ä¸Ģ个好çļĦ
    0.23
    纵è§Ĥ
    0.22
    åĬŀæ³ķ
    0.22
    å°±æĬĬ
    0.21
    çļĦ話
    0.21
    åĿļ强
    0.20
    ä¾¿å®ľ
    0.20
    comparison
    0.19
    æĬĬèĩªå·±çļĦ
    0.18
    Activations Density 0.056%

    No Known Activations