© 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. 25522
    Prev
    Next
    INDEX
    Explanations

    interpolation problem

    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
    计ç®ĹçļĦ
    -0.07
    ç®Ĺ
    -0.07
    ä¸į该
    -0.07
    veli
    -0.06
    认
    -0.06
    触
    -0.06
    eval
    -0.06
    .evaluate
    -0.06
    çĶ¨æ³ķ
    -0.06
    ç®Ĺæľ¯
    -0.06
    POSITIVE LOGITS
    åıªè¦ģèĥ½
    0.09
     problemlos
    0.09
    availability
    0.09
    çļĦæĪIJåĬŁ
    0.09
    大æĬĬ
    0.09
    åı¯ä»¥æ»¡è¶³
    0.09
    Dispon
    0.09
     readily
    0.08
    åıªè¦ģ
    0.08
    edian
    0.08
    Activations Density 0.027%

    No Known Activations