© 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. 13658
    Prev
    Next
    INDEX
    Explanations

    disable something

    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
    ç¾¹
    -0.20
     dụng
    -0.19
    ä¸įéĶĻçļĦ
    -0.18
    æij¹
    -0.18
    stral
    -0.18
    馥
    -0.17
    quest
    -0.17
     uninterrupted
    -0.17
    quis
    -0.17
    ģ
    -0.17
    POSITIVE LOGITS
    æİī
    0.26
    æİīäºĨ
    0.23
    å¤ļä½Ļ
    0.19
    å¤ļä½ĻçļĦ
    0.19
    /on
    0.19
    ä¸įå¿ħè¦ģçļĦ
    0.19
    ä¸ĢåĪĩ
    0.19
    ä»»ä½ķ人
    0.18
    /no
    0.18
    -scrollbar
    0.17
    Activations Density 0.066%

    No Known Activations