© 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. 15663
    Prev
    Next
    INDEX
    Explanations

    legal names and roles

    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
    æĵį
    -0.20
    æľ´å®ŀ
    -0.20
    pick
    -0.19
    让å®ĥ
    -0.19
    -touch
    -0.19
    geist
    -0.19
     plat
    -0.18
    arent
    -0.18
    ARI
    -0.18
    ĵį
    -0.18
    POSITIVE LOGITS
    审议
    0.23
    åĻªéŁ³
    0.22
    èĥľè´Ł
    0.21
    ä¸īæĸ¹
    0.21
    æĭŁ
    0.20
    æī§ä¸ļ
    0.20
    åīįç½®
    0.20
    spath
    0.20
    ä¸Ĭå¹´åIJĮæľŁ
    0.19
    ysz
    0.19
    Activations Density 0.354%

    No Known Activations