© 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. 16640
    Prev
    Next
    INDEX
    Explanations

    Latter-Day Saints

    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
     اÙĦعÙħ
    -0.20
    æű
    -0.18
    plans
    -0.18
     jus
    -0.18
    åģļåĪ°äºĨ
    -0.17
     AGRE
    -0.17
    å·¡èĪª
    -0.17
    ancel
    -0.17
    åĩłä¹İæĺ¯
    -0.17
    apel
    -0.17
    POSITIVE LOGITS
    çļĦçĭ¬çī¹
    0.20
    æĿĤçī©
    0.19
    -spec
    0.19
    è²ī
    0.18
    æĿŀ
    0.18
    é¢ĸ
    0.18
    istring
    0.17
    çĭ¬çī¹
    0.17
    .std
    0.17
    _RESOLUTION
    0.17
    Activations Density 0.001%

    No Known Activations