© 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. 16359
    Prev
    Next
    INDEX
    Explanations

    http links

    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
    åİŁåŀĭ
    -0.23
    æŃĮåĶ±
    -0.21
    ement
    -0.20
    InstanceState
    -0.19
     MPH
    -0.19
    agements
    -0.19
    åĪ¶
    -0.19
     lá»Ļ
    -0.19
    UNET
    -0.18
     Trainer
    -0.18
    POSITIVE LOGITS
    éķĢéĶĮ
    0.20
     affili
    0.20
    éªĪ
    0.19
     lã
    0.19
    è¿Ļè¾¹
    0.19
    èį£å¹¸
    0.19
    æĴµ
    0.19
    é»į
    0.19
    itel
    0.19
    éķ¿å®ī
    0.19
    Activations Density 0.022%

    No Known Activations