© 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. 17146
    Prev
    Next
    INDEX
    Explanations

    version numbers

    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
    ive
    -0.18
    æĴ
    -0.18
     pm
    -0.18
    o
    -0.18
    ific
    -0.17
     Rena
    -0.17
    kas
    -0.17
     Merr
    -0.17
     boom
    -0.17
    ä»ĸ
    -0.17
    POSITIVE LOGITS
    ToFront
    0.22
     wida
    0.21
    å¯Ł
    0.21
    äºĮæľŁ
    0.20
     pornô
    0.20
    æĩ¦
    0.20
    åĨ°åĨ·
    0.19
    ä¸ĢæľŁ
    0.19
    +"'
    0.19
    å¥¥åľ°
    0.19
    Activations Density 0.100%

    No Known Activations