© 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. 48899
    Prev
    Next
    INDEX
    Explanations

    Mr Ishaq's detention

    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
    å·¥ä½ľæĥħåĨµ
    -0.06
    æĺĤ
    -0.06
     ÅĽrodk
    -0.06
    oi
    -0.06
    éĻĦ
    -0.06
    éķĩä¸Ńå¿ĥ
    -0.05
    æľīæĪIJæķĪ
    -0.05
    &S
    -0.05
     rewrite
    -0.05
    adel
    -0.05
    POSITIVE LOGITS
    è¾ĥåݻ年
    0.08
    ='./
    0.08
    ugins
    0.08
    еÑģп
    0.08
    ukat
    0.08
    اجر
    0.08
    appable
    0.08
    spell
    0.07
    андÑĢ
    0.07
    alist
    0.07
    Activations Density 0.008%

    No Known Activations