© 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. 16937
    Prev
    Next
    INDEX
    Explanations

    length of time

    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
    èĻı
    -0.17
    smith
    -0.17
    Äĥn
    -0.16
    ots
    -0.16
    åĭĥåĭĥ
    -0.15
    ëģĶ
    -0.15
    ãĦ§
    -0.15
    onso
    -0.15
    æĢ»é¢Ŀ
    -0.15
    nev
    -0.14
    POSITIVE LOGITS
    ality
    0.22
    =length
    0.19
    éķ¿éķ¿
    0.17
    ally
    0.16
    icity
    0.16
    ism
    0.16
     infancy
    0.16
    æ¯ĶèµĽ
    0.16
    主ä¹ī
    0.16
    å±Ĭ
    0.16
    Activations Density 0.017%

    No Known Activations