© 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. 14597
    Prev
    Next
    INDEX
    Explanations

    legal rights and procedure

    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
    é©·
    -0.21
    atrice
    -0.19
     зан
    -0.19
     побед
    -0.19
    éĽĢ
    -0.19
    çŁ¥åIJį度
    -0.18
    rnd
    -0.18
    åı¦è¡Į
    -0.18
    á¹ħ
    -0.18
    å®ŀåĬĽ
    -0.18
    POSITIVE LOGITS
    .Lock
    0.21
    ouch
    0.19
    flix
    0.18
     karakter
    0.18
    -UA
    0.18
    æĸ°æĶ¿
    0.17
    OfWork
    0.17
    amework
    0.17
    osl
    0.17
     geh
    0.17
    Activations Density 0.005%

    No Known Activations