© 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. 11643
    Prev
    Next
    INDEX
    Explanations

    iOS versions and updates

    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
    å·¥åħ·
    -0.20
     frank
    -0.19
    äºĮèĢħ
    -0.19
     diy
    -0.19
    خار
    -0.19
    æŀĦéĢł
    -0.18
     spor
    -0.18
     Set
    -0.18
    æİ¢
    -0.18
    åīįèĢħ
    -0.18
    POSITIVE LOGITS
    rompt
    0.21
    aired
    0.20
    iba
    0.20
    ủ
    0.20
    omat
    0.19
    eses
    0.19
    ä¸ĭåıij
    0.18
    æľ¬æľĪ
    0.18
    annies
    0.18
    achable
    0.18
    Activations Density 0.050%

    No Known Activations