© 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. 14354
    Prev
    Next
    INDEX
    Explanations

    custody, detention, or held in jail

    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
    æĦŁåıĹ
    -0.21
    åı¤ä»Ĭ
    -0.20
     generous
    -0.19
    äºĴè¡¥
    -0.19
     ÑģоÑĩеÑĤ
    -0.19
    åĬłä¹ĭ
    -0.19
    主æŨ
    -0.19
    åģļå¾Ĺ
    -0.18
     rivalry
    -0.18
     quits
    -0.18
    POSITIVE LOGITS
    presso
    0.23
    ·»
    0.23
    æļĤ
    0.23
    abee
    0.22
     custody
    0.21
    ¶Ī
    0.21
    รà¸Ń
    0.20
    设æĸ½
    0.20
    cust
    0.20
     iÅŁleml
    0.20
    Activations Density 0.035%

    No Known Activations