© 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. 14263
    Prev
    Next
    INDEX
    Explanations

    you know

    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
    REAM
    -0.21
    çŁ¥éģĵèĩªå·±
    -0.20
    æĸ°å¢ŀ
    -0.20
    ãģķãĤĮãĤĭ
    -0.19
    ream
    -0.19
    scribe
    -0.19
    个åĪ«
    -0.18
    绣
    -0.18
    ãĢħ
    -0.18
    å°ijæķ°
    -0.18
    POSITIVE LOGITS
    [,]
    0.20
    è¿Ļæĺ¯æĪij
    0.19
    âĢ°
    0.18
    -scale
    0.17
    /container
    0.17
     pH
    0.17
    请æĤ¨
    0.17
    aring
    0.17
    æĬĬæĪij
    0.17
    ä¿Ĺè¯Ŀ说
    0.17
    Activations Density 0.012%

    No Known Activations