© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 17067
    Prev
    Next
    INDEX
    Explanations

    detection or separation

    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
    Negative Logits
    ä¸į足以
    -0.23
    pch
    -0.19
    oli
    -0.19
    ÐIJÐĹ
    -0.19
    管çIJĨä½ĵåĪ¶
    -0.19
    çĮ¥
    -0.18
    loggedin
    -0.18
    è¡ĮæĶ¿åĮº
    -0.17
     refl
    -0.17
    croft
    -0.17
    POSITIVE LOGITS
    ä¸ºçĽ®çļĦ
    0.22
    ä»»åĬ¡
    0.19
    èĥ½åĬĽå¼º
    0.19
    çī¹çĤ¹æĺ¯
    0.19
     tasks
    0.19
    isSelected
    0.18
    å°ıåŃ©
    0.18
    èĻİ
    0.18
    _without
    0.18
    eventName
    0.18
    Activations Density 0.716%

    No Known Activations