© 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. 16187
    Prev
    Next
    INDEX
    Explanations

    at least

    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
    amp
    -0.23
    ãģ¡ãĤĩãģĨãģ©
    -0.21
     Earlier
    -0.21
    ãģ¾ãģķãģ«
    -0.20
    æѤåīį
    -0.19
    _ROW
    -0.19
    太å°ij
    -0.19
     aslında
    -0.19
    è¿Ľè¡Įåħ¨éĿ¢
    -0.19
    ationship
    -0.19
    POSITIVE LOGITS
    èµ·çłģ
    0.33
    æŁIJç§įç¨ĭ度
    0.26
     partially
    0.24
    èĩ³å°ij
    0.24
    ä¸įä½İäºİ
    0.22
    æľīä¸ĢçĤ¹
    0.22
     partial
    0.21
     Bris
    0.21
    .partial
    0.20
     somewhere
    0.20
    Activations Density 0.032%

    No Known Activations