© 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. 17105
    Prev
    Next
    INDEX
    Explanations

    past critical head specific Maturation

    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
    éĻ·
    -0.26
    é£İæ°Ķ
    -0.22
    çĻĸ
    -0.21
    æī¾
    -0.20
    åĨ¤
    -0.20
    å·§å¦Ļ
    -0.20
     deposit
    -0.20
    亲åŃIJ
    -0.20
    çĺ¾
    -0.20
    åħ¸
    -0.20
    POSITIVE LOGITS
     reportedly
    0.23
    å½ĵåľ°æŶéĹ´
    0.23
    à¸Ĥà¸Ńà¸ĩà¹Ģà¸Ĥา
    0.23
    åģ¥åº·
    0.22
    øy
    0.21
    æĸ¡
    0.21
    _NM
    0.20
    ä»ĸå·²ç»ı
    0.20
    ä½ıéĻ¢
    0.20
    ãģĤãĤĮ
    0.20
    Activations Density 0.047%

    No Known Activations