© 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. 17310
    Prev
    Next
    INDEX
    Explanations

    member or role

    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
     amp
    -0.20
    ве
    -0.19
     ones
    -0.19
    å°ĨæĿ¥
    -0.19
     ostr
    -0.19
    家ä¼Ļ
    -0.18
    ä¸įçĪ±
    -0.18
     Äiju
    -0.18
    éĤ£å°±
    -0.18
     formula
    -0.17
    POSITIVE LOGITS
    ATUS
    0.26
     member
    0.25
    avid
    0.23
    æĪIJåijĺ
    0.23
    å¤ļ次
    0.22
    zell
    0.21
    ANTE
    0.20
     MEMBER
    0.20
    _member
    0.20
    member
    0.19
    Activations Density 0.098%

    No Known Activations