© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 56800
    Prev
    Next
    INDEX
    Explanations

    agreement and continuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    auge
    -0.09
    Courtesy
    -0.08
    æī«ä¸Ģæī«
    -0.08
    é£ŀæī¬
    -0.08
    allery
    -0.08
    .persist
    -0.08
    atype
    -0.08
    vertise
    -0.08
     Sims
    -0.07
    uild
    -0.07
    POSITIVE LOGITS
     next
    0.07
    ,
    0.07
    æĹ¢çĦ¶å¦ĤæѤ
    0.07
     ìĿ´ìłľ
    0.06
    æĹ¢çĦ¶æĺ¯
    0.06
    è¿Ļå°±æĺ¯
    0.06
     proceed
    0.06
    omi
    0.06
    asu
    0.06
    éĹ®é¢ĺæĿ¥äºĨ
    0.06
    Activations Density 0.091%

    No Known Activations