© 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. 12038
    Prev
    Next
    INDEX
    Explanations

    question marks

    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
    è¿ĺåĮħæĭ¬
    -0.22
    åIJĮæŶè¿ĺ
    -0.22
    åħ¶ä½Ļ
    -0.21
    ä½Ĩåį´
    -0.21
    åħ·æľī
    -0.21
    æĺ¯å¤ļä¹Ī
    -0.20
    åij½
    -0.20
    либо
    -0.19
    éĢł
    -0.19
    è¿Ļæł·
    -0.19
    POSITIVE LOGITS
    éŀħ
    0.22
    鸾
    0.20
    egen
    0.20
    езд
    0.20
    ä»ĸ表示
    0.19
    æķĿ
    0.19
    ï¼Īç¬ij
    0.19
    éªĿ
    0.19
    agas
    0.19
    å¢Ģ
    0.19
    Activations Density 0.031%

    No Known Activations