© 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. 16443
    Prev
    Next
    INDEX
    Explanations

    original equipment manufacturing

    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
    åį¦
    -0.21
    eden
    -0.21
    骨
    -0.20
    asher
    -0.20
    æ´»ä¸ĭåİ»
    -0.19
    _python
    -0.19
    /free
    -0.18
    MOTE
    -0.18
    Ùħج
    -0.18
    ä¸ĢèĤ¡
    -0.18
    POSITIVE LOGITS
    å®ĺæĸ¹
    0.31
    æŃ£åĵģ
    0.30
    认åı¯
    0.30
    æŃ£è§Ħ
    0.26
    official
    0.23
     official
    0.23
     Acrobat
    0.23
    åĵģçīĮçļĦ
    0.22
     оÑĢигинал
    0.22
    å®ĺæĸ¹ç½ijç«Ļ
    0.21
    Activations Density 0.029%

    No Known Activations