© 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. 13660
    Prev
    Next
    INDEX
    Explanations

    training programs and opportunities

    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
    ç²ī
    -0.21
    èĢģ人家
    -0.20
    byname
    -0.20
    æĭĤ
    -0.20
    asions
    -0.20
    æīĵåĵį
    -0.19
    modx
    -0.19
    .Attributes
    -0.19
    nowrap
    -0.19
    æĺ¼å¤ľ
    -0.18
    POSITIVE LOGITS
     Ñģпин
    0.23
    ç¡ķ
    0.23
    å¸ĪåħĦ
    0.22
    å·¥ä½ľ
    0.21
     ÑĢоли
    0.20
    çļĦè§Ĵèī²
    0.19
    åѦä½į
    0.19
    stellar
    0.19
    ç§ijçłĶ
    0.18
    /post
    0.18
    Activations Density 0.032%

    No Known Activations