© 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. 12076
    Prev
    Next
    INDEX
    Explanations

    downloads, views, stats

    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
    ARB
    -0.21
    æģª
    -0.21
    ystack
    -0.21
    iglia
    -0.20
    .beginTransaction
    -0.20
    ppe
    -0.20
    adero
    -0.19
    atan
    -0.18
    elli
    -0.18
    åłĨ
    -0.18
    POSITIVE LOGITS
    人次
    0.41
    åĽ´è§Ĥ
    0.24
    次æķ°
    0.23
    traffic
    0.23
     visitors
    0.22
    人æ°Ķ
    0.22
    å°ı鸣
    0.22
    hits
    0.22
     stats
    0.22
    äºĨå¤ļå°ij
    0.21
    Activations Density 0.019%

    No Known Activations