© 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. 14719
    Prev
    Next
    INDEX
    Explanations

    questions asking you to identify something

    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
    æĪŁ
    -0.24
    æĬĵä½ı
    -0.23
    éģĤ
    -0.21
    交ä¼ļ
    -0.21
    åŀĤ
    -0.20
    rub
    -0.20
    oya
    -0.20
    rab
    -0.19
    rat
    -0.19
     pit
    -0.19
    POSITIVE LOGITS
    使çĶ¨çļĦ
    0.20
    å®ĺæĸ¹ç½ijç«Ļ
    0.19
    æĺ¯çĶ±
    0.19
    éĴ¹
    0.19
     بÙĪ
    0.19
    _lex
    0.18
    奶油
    0.18
     Brow
    0.18
    cascade
    0.18
    оваÑĢ
    0.18
    Activations Density 0.008%

    No Known Activations