© 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. 10534
    Prev
    Next
    INDEX
    Explanations

    url encoding with %3

    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
    les
    -0.23
    ment
    -0.23
    self
    -0.21
    对åħ¶çľŁå®ŀ
    -0.20
    le
    -0.20
    after
    -0.20
    User
    -0.19
    utes
    -0.19
    List
    -0.19
    Con
    -0.19
    POSITIVE LOGITS
    hợ
    0.29
    ãĮ¢
    0.23
    há»ı
    0.23
    eiÃŁ
    0.22
    há»ķ
    0.22
    ãģĦãĤīãģ£
    0.21
    europäische
    0.21
    põe
    0.21
     aalborg
    0.21
    ãģĬãģĻãģĻ
    0.20
    Activations Density 0.181%

    No Known Activations