© 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. 13224
    Prev
    Next
    INDEX
    Explanations

    games played and appearances

    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
    ä¼į
    -0.22
    满满
    -0.21
    水管
    -0.19
    woord
    -0.19
    榷
    -0.19
    errs
    -0.19
    borough
    -0.18
    ç¾ŀ
    -0.18
    æīĵæŃ»
    -0.18
    ç«
    -0.18
    POSITIVE LOGITS
    æľįä»İ
    0.20
    è§ģè¿ĩ
    0.19
    YPE
    0.19
    éĥ½æľīçĿĢ
    0.19
    ãģķ
    0.19
    éĥ½æ²¡
    0.18
    ä¸ī次
    0.18
    synthesize
    0.18
    åľ»
    0.18
     clearfix
    0.18
    Activations Density 0.005%

    No Known Activations