© 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. 14528
    Prev
    Next
    INDEX
    Explanations

    .requesturlopen

    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
    人家
    -0.20
     ratt
    -0.19
    å·²ä¹ħ
    -0.19
    .GetHashCode
    -0.19
    åĪ®
    -0.18
    acc
    -0.18
    oku
    -0.18
    åĬ²
    -0.18
    åij¨åĽ´
    -0.18
    -pages
    -0.18
    POSITIVE LOGITS
     PaÅĦstwo
    0.19
    rael
    0.19
    InThe
    0.19
    _errno
    0.18
    Mixin
    0.18
    ãĤ¿ãĥ³
    0.17
    _EPS
    0.17
    stants
    0.17
    Helper
    0.17
    stances
    0.17
    Activations Density 0.665%

    No Known Activations