© 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. 12726
    Prev
    Next
    INDEX
    Explanations

    getaway and escape

    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
    ä½ĵè´¨
    -0.19
    禧
    -0.19
    ç´¢èµĶ
    -0.19
    ullo
    -0.19
    稿
    -0.18
    /lic
    -0.18
     Elias
    -0.17
    æĻĶ
    -0.17
    è¿Ļæĺ¯ä¸Ģç§į
    -0.17
    èĦį
    -0.17
    POSITIVE LOGITS
    ä¸į失
    0.23
    ustin
    0.22
    ç»Ŀ
    0.20
    æĶ¾æĿ¾
    0.20
    ä¹ĭæīĢ
    0.19
     getaway
    0.19
    Accessible
    0.19
    éĢĥ离
    0.19
    ä¹ĭåľ°
    0.19
    _RESPONSE
    0.18
    Activations Density 0.009%

    No Known Activations