© 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. 12905
    Prev
    Next
    INDEX
    Explanations

    capturing images, text, or data

    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
    atically
    -0.20
    ega
    -0.19
    entifier
    -0.19
     xuyên
    -0.17
    shake
    -0.17
    avier
    -0.17
    í
    -0.16
    eners
    -0.16
    esis
    -0.16
    esty
    -0.15
    POSITIVE LOGITS
    èĻı
    0.21
    äºĨ许å¤ļ
    0.21
    ä½ıäºĨ
    0.19
    ustin
    0.19
    äºĨä¸įå°ij
    0.18
    inus
    0.18
    ä¸įäºĨ
    0.17
    /generated
    0.17
    åħ±é¸£
    0.16
    äºĨå¤ļå°ij
    0.16
    Activations Density 0.017%

    No Known Activations