© 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. 14409
    Prev
    Next
    INDEX
    Explanations

    copyright and license information

    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
    é³ŀ
    -0.20
    èĵ¬åĭĥ
    -0.19
    PROTO
    -0.19
    LOGGER
    -0.19
     Dev
    -0.19
     Pres
    -0.18
    lash
    -0.17
     pod
    -0.17
    æıŃ
    -0.17
    å¥ķ
    -0.17
    POSITIVE LOGITS
    ered
    0.21
    eko
    0.19
    enan
    0.19
    éģĹæ¼ı
    0.19
    åĿıäºĭ
    0.19
    èįª
    0.18
    为æѤ
    0.18
    å£ķ
    0.18
    对æѤ
    0.18
    .dk
    0.18
    Activations Density 0.213%

    No Known Activations