© 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. 14814
    Prev
    Next
    INDEX
    Explanations

    transparency, openness, information, logging

    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
    çĭ¬æľīçļĦ
    -0.21
    åIJĮèĥŀ
    -0.19
    ç¦Ģ
    -0.19
    çĶŁçIJĨ
    -0.19
    åIJįå¸Ī
    -0.18
    drug
    -0.18
    tep
    -0.18
    à¹Ģล
    -0.18
    æī¾åĽŀ
    -0.18
    mine
    -0.18
    POSITIVE LOGITS
    éĢıæĺİ
    0.32
    åħ¬å¼Ģ
    0.28
     Transparent
    0.26
     transparency
    0.26
     transparent
    0.25
     Transparency
    0.24
    éĺ³åħī
    0.23
     púb
    0.22
    -publish
    0.21
     publicly
    0.20
    Activations Density 0.018%

    No Known Activations