© 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. 13718
    Prev
    Next
    INDEX
    Explanations

    proper nouns and places

    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
    ä¼łéĢĴ
    -0.21
    lien
    -0.20
    UNG
    -0.19
    å¯ĵ
    -0.18
    ipi
    -0.18
    .Unlock
    -0.18
    èµ·åĪ°äºĨ
    -0.18
    ä½ľ
    -0.18
    ault
    -0.18
    ric
    -0.18
    POSITIVE LOGITS
    ä¹Łä¸įä¾ĭå¤ĸ
    0.24
    åĿļæĮģ以
    0.21
    ä¹Łæĺ¯å¦ĤæѤ
    0.20
    ãģ¨ãģ¯ãģĦãģĪ
    0.20
    éĢĤçĶ¨
    0.20
    沿éĢĶ
    0.19
    ĥĿ
    0.18
    åĥ»
    0.18
     mxArray
    0.18
    åľ¨çĶŁæ´»ä¸Ń
    0.18
    Activations Density 0.501%

    No Known Activations