© 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. 10665
    Prev
    Next
    INDEX
    Explanations

    cataracts

    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
    ãĥ¡ãĥ³ãĥĪ
    -0.20
    çĻĸ
    -0.20
    à¤ł
    -0.19
    åĨ»
    -0.19
    æħ£
    -0.19
    ollower
    -0.19
    é¢ł
    -0.18
    å°±æĺ¯è¦ģ
    -0.18
    alte
    -0.17
     Way
    -0.17
    POSITIVE LOGITS
    åįľ
    0.20
    äºĨ解åĪ°
    0.20
    (CL
    0.20
    banks
    0.20
    éĻĽ
    0.19
    å¤ĸå½¢
    0.19
    fy
    0.18
    éķ¿èĢģ
    0.18
    ius
    0.18
    ones
    0.18
    Activations Density 0.010%

    No Known Activations