© 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. 16073
    Prev
    Next
    INDEX
    Explanations

    academic degrees

    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
    /dc
    -0.20
    umed
    -0.18
    æ°
    -0.18
    åľ°åĿª
    -0.18
    umph
    -0.17
    .mozilla
    -0.17
    é²
    -0.17
    evin
    -0.17
    ILA
    -0.17
     Uncle
    -0.17
    POSITIVE LOGITS
    å°±è§īå¾Ĺ
    0.21
    _FD
    0.21
    æ¦Ń
    0.19
    æľīæľº
    0.19
     scar
    0.19
    大äºĭ
    0.18
     domination
    0.18
    å®ĮæĪIJåIJİ
    0.17
    æĹ¶æľŁçļĦ
    0.17
     Coll
    0.17
    Activations Density 0.027%

    No Known Activations