© 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. 14751
    Prev
    Next
    INDEX
    Explanations

    legal citations

    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
    aida
    -0.21
    ä¸įæ¸ħ
    -0.20
    åħ¥åĽ´
    -0.19
     Äijứng
    -0.19
    ªĮ
    -0.19
    .readline
    -0.18
    秩
    -0.18
    strap
    -0.18
    &s
    -0.18
    ÑĢоÑģл
    -0.17
    POSITIVE LOGITS
    硬åĮĸ
    0.23
    pst
    0.20
    ICC
    0.19
    iran
    0.19
    åĮ»çĸĹåį«çĶŁ
    0.18
    滦
    0.18
    åĪ¨
    0.18
    ç¼ĸ
    0.18
    é«ĺçŃīåŃ¦æł¡
    0.18
    ADIUS
    0.18
    Activations Density 0.023%

    No Known Activations