© 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. 12780
    Prev
    Next
    INDEX
    Explanations

    articles followed by nouns or determiners

    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
    éĶIJ
    -0.20
    enc
    -0.20
    ier
    -0.20
    æľ¬å½ĵ
    -0.19
    orm
    -0.19
    abd
    -0.18
    amber
    -0.18
    sey
    -0.17
    icos
    -0.17
    rzy
    -0.17
    POSITIVE LOGITS
    æĪIJåĬŁçļĦ
    0.19
    åıijè¨Ģ人
    0.19
    åįİ侨
    0.17
    åIJ¬å®Į
    0.17
     Success
    0.17
    éĵŁ
    0.16
     Rencontres
    0.16
    èµĸ以
    0.16
    å¹½é»ĺ
    0.16
    太太
    0.16
    Activations Density 0.056%

    No Known Activations