© 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. 11928
    Prev
    Next
    INDEX
    Explanations

    rhythmic gymnast, clubs, jousting

    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
    ieves
    -0.20
    çĺĹ
    -0.20
    iever
    -0.20
    witter
    -0.18
    ateway
    -0.18
    èģĶåIJĪ
    -0.18
    çīĪ
    -0.18
    åł¡åŀĴ
    -0.18
    æī¼
    -0.18
     Prev
    -0.17
    POSITIVE LOGITS
    表æ¼Ķ
    0.29
    sticks
    0.25
    éĵī
    0.24
    çĪ±å¥½
    0.23
    åĻ¨æĿIJ
    0.22
    达人
    0.21
    é«ĺæ°´å¹³
    0.20
     sticks
    0.20
    æķĻç¨ĭ
    0.20
    ç¼ł
    0.20
    Activations Density 0.006%

    No Known Activations