© 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. 38579
    Prev
    Next
    INDEX
    Explanations

    it is

    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
    ä¸ĢæľĽ
    -0.08
    设å¤ĩè¿Ľè¡Į
    -0.08
    unker
    -0.08
    ãģĿãģĵãģ«
    -0.08
    对该
    -0.08
    å°įæѤ
    -0.08
    ctest
    -0.07
    å°ĨæѤ
    -0.07
    å°Ĩä¼ļæľī
    -0.07
     ensued
    -0.07
    POSITIVE LOGITS
    å®ĥåı¯ä»¥
    0.11
    å®ĥ
    0.10
    å®ĥæĺ¯
    0.10
    å®ĥçļĦ
    0.09
    ä½Ĩå®ĥ
    0.09
    å®ĥåľ¨
    0.09
    主è¦ģçĶ¨äºİ
    0.09
    å®ĥ对
    0.08
     Nó
    0.08
    åĽłä¸ºå®ĥ
    0.08
    Activations Density 0.683%

    No Known Activations