© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10731
    Prev
    Next
    INDEX
    Explanations

    license, package, or author names

    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
     phá»ij
    -0.20
    èĥĸåŃIJ
    -0.19
    olie
    -0.19
    red
    -0.18
    é¹ı
    -0.18
    ark
    -0.18
    PerPixel
    -0.17
    íijľ
    -0.17
    ris
    -0.17
    ull
    -0.16
    POSITIVE LOGITS
    centage
    0.24
    formance
    0.23
    folio
    0.23
    ICTURE
    0.21
    ively
    0.20
    ynomial
    0.19
    seudo
    0.19
    innacle
    0.19
    ï¬ĥ
    0.19
    thag
    0.18
    Activations Density 6.851%

    No Known Activations