© 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. 15616
    Prev
    Next
    INDEX
    Explanations

    academic citations with superscripts

    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
    .Dock
    -0.19
    éĶħ
    -0.19
    å°ijçĪ·
    -0.19
    åīįèĢħ
    -0.19
    æ¼¾
    -0.18
    çľ¼ä¸Ń
    -0.18
    éįĭ
    -0.18
    åĵĿ
    -0.18
    å¯IJ
    -0.18
     Alcohol
    -0.17
    POSITIVE LOGITS
    cip
    0.20
    移åĪ°
    0.19
    åĩŃåĢŁ
    0.19
    ä½ĵè´¨
    0.19
     DBG
    0.19
     da
    0.19
    åºı
    0.18
    æѤæŶ
    0.18
    avis
    0.18
    ç½®
    0.18
    Activations Density 0.021%

    No Known Activations