© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 17018
    Prev
    Next
    INDEX
    Explanations

    nesting and habitats

    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
    ä¸ĭ车
    -0.25
    马åĬĽ
    -0.20
    èħ»
    -0.20
    ulg
    -0.20
     еÑī
    -0.20
    pany
    -0.19
    é©´
    -0.19
    plat
    -0.19
    agues
    -0.18
    orld
    -0.18
    POSITIVE LOGITS
    ç©´
    0.29
    éĢīåĿĢ
    0.24
    å·¢
    0.24
    èĤ²
    0.23
    家åºŃ
    0.23
    èĤ²åĦ¿
    0.23
    æIJŃ建
    0.22
    ç¹ģæ®ĸ
    0.22
    æĸ°æīĭ
    0.22
    亲åŃIJ
    0.22
    Activations Density 0.027%

    No Known Activations