© 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. 11157
    Prev
    Next
    INDEX
    Explanations

    shallow and narrow conditions

    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
    æīĢåľ¨åľ°
    -0.20
    asics
    -0.19
    åĽĬ
    -0.19
    .har
    -0.19
    æ¯ĽåŃĶ
    -0.19
    容è²Į
    -0.19
    asel
    -0.18
    ardin
    -0.18
     greatest
    -0.18
    èĸı
    -0.18
    POSITIVE LOGITS
    /small
    0.24
    æīĭèĦļ
    0.23
    ä¸Ķ
    0.20
    -than
    0.19
    çĽĺ
    0.18
     Schultz
    0.18
    -profile
    0.18
    纯
    0.18
     FileUtils
    0.18
    沪深
    0.18
    Activations Density 0.032%

    No Known Activations