© 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. 13202
    Prev
    Next
    INDEX
    Explanations

    gas and

    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
    èĤ¥
    -0.20
    .assertj
    -0.20
    èĢ»
    -0.18
    æįº
    -0.18
    ãĤĤãģ£ãģ¨
    -0.18
    mares
    -0.18
    lander
    -0.18
     Morrow
    -0.18
    theid
    -0.18
    éĶŃ
    -0.18
    POSITIVE LOGITS
     Buch
    0.19
    è®°èĢħ
    0.19
     candle
    0.19
     battle
    0.19
    æ³¼
    0.18
     Jad
    0.18
    å¢Ļå£ģ
    0.18
    adem
    0.18
    uder
    0.18
    糸
    0.18
    Activations Density 0.013%

    No Known Activations