© 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. 12805
    Prev
    Next
    INDEX
    Explanations

    U.S. Pat. No

    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
    iscal
    -0.22
    åĽłä¸ºæĪij们
    -0.21
     ÐIJлекÑģан
    -0.20
     заÑĢегиÑģÑĤ
    -0.20
     меÑĢоп
    -0.20
     beh
    -0.19
    èĢij
    -0.19
    (beta
    -0.19
    ä¸ĭ次
    -0.19
     extr
    -0.18
    POSITIVE LOGITS
    æĸĩçĮ®
    0.21
    åĪ©äºļ
    0.20
     пÑĢакÑĤиÑĩеÑģ
    0.20
    åĻ
    0.20
    AuthToken
    0.20
    çĿĢçľ¼äºİ
    0.19
    æŀĹä¸ļ
    0.19
    ç»ıåħ¸çļĦ
    0.18
     Locked
    0.18
    ",__
    0.18
    Activations Density 0.436%

    No Known Activations