© 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. 11041
    Prev
    Next
    INDEX
    Explanations

    good followed by a noun

    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
    åIJ¾
    -0.19
    AZE
    -0.18
    iens
    -0.18
    ders
    -0.18
     Dude
    -0.18
    ä¸İä¸ŃåĽ½
    -0.17
    ema
    -0.17
    æİĴåĩº
    -0.17
    ION
    -0.17
    erek
    -0.17
    POSITIVE LOGITS
    åĭģ
    0.24
    èĥ½çľĭåĩº
    0.24
    ä¸Ģ个好çļĦ
    0.23
     Ñģобой
    0.21
    ä¸Ģ个å°ıæŶ
    0.21
    éĢĤåIJĪèĩªå·±
    0.21
    åĬ²
    0.21
    -sized
    0.20
    æľĢéļ¾
    0.20
    -quality
    0.20
    Activations Density 0.058%

    No Known Activations