© 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. 13273
    Prev
    Next
    INDEX
    Explanations

    registered retirement income fund

    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
    urent
    -0.18
    ÑģÑĤÑĭ
    -0.18
    mediate
    -0.18
     dex
    -0.18
    OMET
    -0.18
    us
    -0.17
    _UT
    -0.17
     зав
    -0.17
    ob
    -0.17
    unu
    -0.17
    POSITIVE LOGITS
    à¹Ģà¸Ħ
    0.18
    åĨ²åĩ»
    0.18
    嵯
    0.18
    ئة
    0.17
    æ¾į
    0.17
    .kr
    0.17
    çIJ°
    0.17
    æĺ¯åı¯ä»¥
    0.17
    gp
    0.17
    bern
    0.17
    Activations Density 0.002%

    No Known Activations