© 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. 15535
    Prev
    Next
    INDEX
    Explanations

    today I can identify

    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
    s
    -0.24
    ‘
    -0.19
     rer
    -0.19
    V
    -0.18
     Ret
    -0.18
     '
    -0.18
    âĢİ
    -0.18
    p
    -0.17
    rou
    -0.17
     track
    -0.17
    POSITIVE LOGITS
    etheless
    0.26
    iếc
    0.20
    odore
    0.20
    æĮ£æīİ
    0.19
    oretical
    0.19
    æĢİä¹Īçľĭ
    0.18
    ä»Ģä¹ĪæŶåĢĻ
    0.18
    éĽĴ
    0.18
    åĴĦ
    0.18
    ологиÑı
    0.18
    Activations Density 0.010%

    No Known Activations