© 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. 16912
    Prev
    Next
    INDEX
    Explanations

    originating from

    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
    иÑĩеÑģкий
    -0.21
    atorial
    -0.20
    æĪĸå¤ļ
    -0.20
    æѤäºĭ
    -0.20
    åĽĽçº§
    -0.19
    ä»įæľī
    -0.19
     Laden
    -0.18
    ä»Ģä¹Īåij¢
    -0.18
    ä¸ļåĬ¡
    -0.18
    ãģ³
    -0.18
    POSITIVE LOGITS
     scratch
    0.26
     standpoint
    0.24
     whence
    0.23
    ä¸Ģå¼Ģå§ĭå°±
    0.23
     perspective
    0.23
     outset
    0.23
     inception
    0.22
    å¾Īä½İ
    0.21
     start
    0.21
    åĽĽä¸ªæĸ¹éĿ¢
    0.21
    Activations Density 0.157%

    No Known Activations