© 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. 13126
    Prev
    Next
    INDEX
    Explanations

    located in or at

    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
    çij°
    -0.23
    iteit
    -0.20
    agar
    -0.20
    åıĪä¸Ģ次
    -0.19
    æıIJåīį
    -0.19
    _OPER
    -0.19
    uale
    -0.19
    çľĭä¸įæĩĤ
    -0.19
    zew
    -0.19
    asn
    -0.18
    POSITIVE LOGITS
    æĽ¾
    0.28
    æĽ¾ç»ı
    0.28
    ä½Ĩçİ°åľ¨
    0.26
    çİ°åľ¨å·²ç»ı
    0.26
    è¾īçħĮ
    0.26
    ä¸Ģ段æŶéĹ´
    0.26
    åģļè¿ĩ
    0.25
    æĽ¾ç¶ĵ
    0.23
     Former
    0.23
     æĽ
    0.23
    Activations Density 0.253%

    No Known Activations