© 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. 16048
    Prev
    Next
    INDEX
    Explanations

    words ending in ities

    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
    ä¹ĭç±»çļĦ
    -0.23
    ä¹ĭç±»
    -0.22
    å±Ĥåĩº
    -0.21
    ç¬ı
    -0.21
    æĪĸèĢħåħ¶ä»ĸ
    -0.19
    æŁIJç§į
    -0.19
    åĮį
    -0.19
    å°±ç»Ļ大家
    -0.19
     kn
    -0.19
    çķĽ
    -0.19
    POSITIVE LOGITS
    вÑĥ
    0.21
    ä¹ŁæĪIJ为
    0.20
    oca
    0.19
    _ACK
    0.19
    ulong
    0.19
    çĿ¨
    0.19
    红æĺŁ
    0.18
    æĸĩåĮĸåĴĮ
    0.18
    å®ł
    0.18
    ÑĩеÑĤ
    0.18
    Activations Density 0.448%

    No Known Activations