© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10438
    Prev
    Next
    INDEX
    Explanations

    CWE and filenames

    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
    Negative Logits
     Pf
    -0.19
    åİŁæĸĩåľ°åĿĢ
    -0.18
     Nelson
    -0.18
    æĦŁè°¢
    -0.18
    æĦı
    -0.18
    vc
    -0.17
     Terry
    -0.17
    çľĭ
    -0.17
     Trend
    -0.17
     journey
    -0.17
    POSITIVE LOGITS
    loo
    0.20
    çªŁ
    0.20
    è¢ľ
    0.19
    è·º
    0.19
    æİ°
    0.18
    ⽬
    0.18
    porno
    0.18
    æĻ¦
    0.18
    Callbacks
    0.18
    æ£ĺ
    0.18
    Activations Density 0.385%

    No Known Activations