© 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. 13013
    Prev
    Next
    INDEX
    Explanations

    compensation, evaluation, and performance

    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
    wä
    -0.22
    太ä¹ħ
    -0.21
    åı¯æĮģç»Ń
    -0.19
    çĥĤ
    -0.18
    imed
    -0.18
     далÑĮ
    -0.18
    æ¶ĪåĮĸ
    -0.18
    /products
    -0.18
     CLUB
    -0.17
    à¹ģà¸ĸ
    -0.17
    POSITIVE LOGITS
    åĪ¶åº¦æĶ¹éĿ©
    0.23
    èµ·æĿ¥äºĨ
    0.19
    ivil
    0.19
    illac
    0.19
    èģĺçĶ¨
    0.19
    advisor
    0.18
    uros
    0.18
    æ¤Ĵ
    0.18
     Killing
    0.18
    anko
    0.18
    Activations Density 0.006%

    No Known Activations