© 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. 14682
    Prev
    Next
    INDEX
    Explanations

    static, especially in code documentation

    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
    ings
    -0.22
    hone
    -0.19
    INGS
    -0.17
    åĴĮåľ°åĮº
    -0.17
    çľļ
    -0.17
    licit
    -0.16
    alto
    -0.16
    hart
    -0.15
    trim
    -0.15
    half
    -0.15
    POSITIVE LOGITS
    tics
    0.27
    åĮĸçļĦ
    0.21
     readonly
    0.21
    ifies
    0.19
    /manual
    0.18
    -minded
    0.18
    y
    0.17
    itics
    0.17
    busters
    0.17
     propTypes
    0.17
    Activations Density 0.035%

    No Known Activations