© 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. 12153
    Prev
    Next
    INDEX
    Explanations

    immerse yourself in the world

    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
    åIJĥè¿ĩ
    -0.21
    æĽĻåħī
    -0.20
    éĢłç¦ı
    -0.20
    ukes
    -0.20
    индивид
    -0.20
    akedown
    -0.19
    éĿ¢ä¸Ĭ
    -0.19
    åIJ¬å¾Ĺ
    -0.19
    æĻ¾
    -0.19
    ä¿Ŀé²ľ
    -0.19
    POSITIVE LOGITS
    æ²ī浸
    0.29
    æĦıå¢ĥ
    0.25
    æĬķåħ¥åĪ°
    0.23
     immersive
    0.22
    æĬķåħ¥
    0.22
    å¿ĺè®°äºĨ
    0.20
     into
    0.20
     reality
    0.20
     depth
    0.20
    å¿ĺ
    0.19
    Activations Density 0.026%

    No Known Activations