© 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. 14373
    Prev
    Next
    INDEX
    Explanations

    Macedonian

    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
    éķľå¤´
    -0.18
    å»Ľ
    -0.18
    åĻİ
    -0.18
    ccount
    -0.18
    è¿Ľåĩº
    -0.18
    Nib
    -0.18
    仪表
    -0.17
     dunk
    -0.17
    çݳ
    -0.17
    éĩįåºĨå¸Ĥ
    -0.17
    POSITIVE LOGITS
     Maced
    0.23
     Bulgarian
    0.22
    falls
    0.20
    inging
    0.19
    emente
    0.19
    eva
    0.19
    okia
    0.18
    abad
    0.18
    _HIT
    0.18
    -born
    0.17
    Activations Density 0.009%

    No Known Activations