© 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. 13334
    Prev
    Next
    INDEX
    Explanations

    incubating or incubation

    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
    è´¨
    -0.20
    é«ĺä½į
    -0.20
    insk
    -0.20
    mobx
    -0.20
    AtA
    -0.20
    icens
    -0.20
    .gca
    -0.19
    éŀł
    -0.19
    å±ı
    -0.19
    eker
    -0.19
    POSITIVE LOGITS
    either
    0.26
    åѵ
    0.25
    probe
    0.23
    æŶéĹ´ä¸º
    0.22
    ãĤ¿ãĤ¤ãĥł
    0.21
    èµĽåIJİ
    0.21
    ëĭ¤ê°Ģ
    0.21
     каждÑĭй
    0.21
    time
    0.20
    æĻĤéĸĵ
    0.20
    Activations Density 0.896%

    No Known Activations