© 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. 16544
    Prev
    Next
    INDEX
    Explanations

    .org, .com, or corp

    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
    ippo
    -0.21
    ç´ł
    -0.20
    çĮĿ
    -0.20
    atty
    -0.20
    ITER
    -0.19
    çĪĨåĩº
    -0.19
    igit
    -0.19
     jitter
    -0.18
    haul
    -0.18
    俾
    -0.18
    POSITIVE LOGITS
    /posts
    0.23
    åѦåłĤ
    0.21
    éĺ´è°ĭ
    0.21
    çļĦçĪ±æĥħ
    0.21
     Thesis
    0.20
    æĬĢå¸Ī
    0.19
     Oval
    0.19
    澳大
    0.18
    uyo
    0.18
    åĪĿæģĭ
    0.18
    Activations Density 0.173%

    No Known Activations