© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15238
    Prev
    Next
    INDEX
    Explanations

    email suffixes

    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
    idget
    -0.23
    pod
    -0.22
    .asp
    -0.21
     gig
    -0.20
    nie
    -0.20
    çĽijåIJ¬é¡µéĿ¢
    -0.20
    law
    -0.20
    iner
    -0.19
     hoof
    -0.19
     Cultural
    -0.19
    POSITIVE LOGITS
     NodeList
    0.23
    toMatchSnapshot
    0.22
    ä¹ĺçĶ¨è½¦
    0.21
    åij£
    0.21
    æ£Ģä¿®
    0.20
     Broadcom
    0.20
    主è¦ģæľī
    0.20
    æĮĩ导ä¸ĭ
    0.20
    emplace
    0.19
     Florian
    0.19
    Activations Density 0.484%

    No Known Activations