© 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. 10450
    Prev
    Next
    INDEX
    Explanations

    "I, for one"

    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
    è¿Ļ让
    -0.22
    ä½Ĩå®ĥ
    -0.21
    è¿Ļæĺ¯åĽłä¸º
    -0.21
    çīĮåŃIJ
    -0.20
    è¿Ļæł·ä¸ĢæĿ¥
    -0.20
    è¿Ļ对äºİ
    -0.20
    è¿Ļä¸ĢçĤ¹
    -0.19
    åĴ¦
    -0.19
    éĤ£æł·
    -0.19
    为äºĨ让
    -0.19
    POSITIVE LOGITS
    æīįæĺ¯
    0.21
    alone
    0.20
     alone
    0.19
     Norton
    0.19
    enburg
    0.18
    verts
    0.17
    $LANG
    0.17
    er
    0.17
    _ratings
    0.17
    minate
    0.17
    Activations Density 0.031%

    No Known Activations