© 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. 15510
    Prev
    Next
    INDEX
    Explanations

    abstract nouns denoting states or processes

    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
    æĹłæķ°
    -0.22
    ä»ģ
    -0.21
    åijĬè¯ī
    -0.21
    对çĿĢ
    -0.21
    åĸ»
    -0.21
    åľ¨åĨħçļĦ
    -0.20
    çľĭ
    -0.19
    åijĬè¯īä»ĸ
    -0.19
    åijĬè¯īä½ł
    -0.18
    éĢļè¿ĩ对
    -0.18
    POSITIVE LOGITS
    ensively
    0.22
    æĸ¹éĿ¢
    0.22
     behalf
    0.21
    è¿Ļ件äºĭæĥħ
    0.21
    lá
    0.19
    è¿Ļæī¹
    0.18
     vad
    0.18
    .people
    0.17
    fef
    0.17
    è¿Ļ段
    0.17
    Activations Density 0.620%

    No Known Activations