© 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. 13633
    Prev
    Next
    INDEX
    Explanations

    abbreviations followed by periods

    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
    èµĸ以
    -0.23
    åĵ¥
    -0.19
    åµ´
    -0.19
    æľīåĪ©
    -0.19
    ä¸įåĪ©
    -0.18
    intl
    -0.18
    è§Ĭ
    -0.18
    known
    -0.18
    imp
    -0.18
    è¶ħ
    -0.18
    POSITIVE LOGITS
     Hearth
    0.19
    lopedia
    0.18
    UnderTest
    0.18
    LER
    0.17
    çħĭ
    0.17
    (ml
    0.17
     Yield
    0.16
     ÑĢеж
    0.16
    为广大
    0.16
    åİĨåı²æĸ°
    0.16
    Activations Density 0.021%

    No Known Activations