© 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. 12951
    Prev
    Next
    INDEX
    Explanations

    vehicle guidance and repair

    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
    çļ±çº¹
    -0.22
    /up
    -0.20
     Zuk
    -0.18
    æĤĽ
    -0.18
     backwards
    -0.18
     punch
    -0.17
    çħ³
    -0.17
    (coeffs
    -0.17
    梦è§ģ
    -0.17
     punches
    -0.17
    POSITIVE LOGITS
    åľ¨éĤ£éĩĮ
    0.25
    çĽĪ
    0.24
    urally
    0.24
    pit
    0.24
    æĹħ
    0.23
    åľ¨è¿ĻéĩĮ
    0.23
    带ä¸Ĭ
    0.22
    人士
    0.21
    æĿ¥è¿ĻéĩĮ
    0.21
    便ä¼ļ
    0.21
    Activations Density 0.113%

    No Known Activations