© 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. 24212
    Prev
    Next
    INDEX
    Explanations

    equipment names

    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
     Nets
    -0.07
    è§Ħ模
    -0.06
     harmless
    -0.06
    ä¿Ŀé²ľ
    -0.06
     escal
    -0.06
    ä½İæĪIJæľ¬
    -0.06
    è¾ĵ
    -0.06
    IGA
    -0.06
    ä¾ĿéĻĦ
    -0.06
    裳
    -0.06
    POSITIVE LOGITS
     aftermarket
    0.09
    é«ĺæ¡¥
    0.09
    å®ĺæĸ¹å¾®ä¿¡
    0.08
     stance
    0.08
    æĶ¶äºİ
    0.08
    æĪĺåĮº
    0.08
    âĤ¬“
    0.08
    ä¸Ńé«ĺ端
    0.08
    çłĶ磨
    0.08
     biome
    0.08
    Activations Density 0.213%

    No Known Activations