© 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. 16107
    Prev
    Next
    INDEX
    Explanations

    age

    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
    ero
    -0.18
    ilor
    -0.17
    åıįä¹ĭ
    -0.17
    æij¸ç´¢
    -0.16
    upert
    -0.16
    eros
    -0.16
    abant
    -0.16
     gust
    -0.16
    lopedia
    -0.16
    bian
    -0.15
    POSITIVE LOGITS
    -fashioned
    0.30
     fashioned
    0.20
    entifier
    0.20
    liness
    0.19
    ãģĭãģªãģĦ
    0.18
    ness
    0.18
    0.18
    ocities
    0.17
    ä»»æľŁ
    0.17
    åĴĮåľ°åĮº
    0.16
    Activations Density 0.015%

    No Known Activations