© 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. 15614
    Prev
    Next
    INDEX
    Explanations

    methods to save

    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
    çIJ¦
    -0.21
    anda
    -0.18
    areth
    -0.18
     Baldwin
    -0.17
    DED
    -0.17
    ä¼¢
    -0.17
     bowling
    -0.17
    wers
    -0.17
    teil
    -0.17
    AMB
    -0.17
    POSITIVE LOGITS
    ýt
    0.21
    åģı
    0.20
    ÑģÑĤоÑı
    0.19
    batim
    0.19
    岬
    0.18
     Fabric
    0.18
    mı
    0.17
    اخر
    0.17
    éĿŀ常
    0.17
    æľĿ
    0.17
    Activations Density 0.192%

    No Known Activations