© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12235
    Prev
    Next
    INDEX
    Explanations

    Facebook, Hitman, Bookmobile

    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
    hip
    -0.21
    èįľ
    -0.20
    é¢ijé¢ij
    -0.19
    èĩĬ
    -0.19
    ush
    -0.18
     Moy
    -0.18
    èµ·æĿ¥
    -0.18
    åĵ©
    -0.18
    çijļ
    -0.18
    åķ
    -0.17
    POSITIVE LOGITS
    åĿĿ
    0.19
    ghan
    0.18
     Fountain
    0.17
     uçu
    0.17
    modx
    0.17
    ãĥĬãĥ³
    0.17
    æĪĸ
    0.17
    æľīæķĪ
    0.17
     charset
    0.17
    egas
    0.17
    Activations Density 0.001%

    No Known Activations