© 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. 10920
    Prev
    Next
    INDEX
    Explanations

    reflexive pronouns followed by "as" or "to"

    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
    çľĭä¸Ĭåİ»
    -0.23
    çľĭä¼¼
    -0.21
    çľĭèµ·æĿ¥
    -0.20
    声åĵį
    -0.20
    rück
    -0.19
    ç»Ĥ
    -0.19
    空æ°Ķä¸Ń
    -0.18
    Appear
    -0.18
    /bus
    -0.18
    æŧ
    -0.18
    POSITIVE LOGITS
    å®ļä½į
    0.24
     multid
    0.21
    æľīè¶³å¤ŁçļĦ
    0.20
    TeX
    0.20
    bis
    0.19
    æīĢå±ŀ
    0.19
    ROLE
    0.19
     boast
    0.18
    Gro
    0.18
    ï¸ı
    0.18
    Activations Density 0.027%

    No Known Activations