© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15029
    Prev
    Next
    INDEX
    Explanations

    program strings

    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
    éļħ
    -0.07
    ä¸įèµ°
    -0.07
    _seek
    -0.07
    ắm
    -0.07
    å·¥
    -0.07
    å°ļåľ¨
    -0.07
    ä¸įä½ľ
    -0.06
    天ä¹ĭ
    -0.06
    对å¤ĸ
    -0.06
     ìĿµ
    -0.06
    POSITIVE LOGITS
    ashian
    0.07
    arrass
    0.07
    SHA
    0.07
    elib
    0.07
    è§ĤæľĽ
    0.06
    bergen
    0.06
    æĸĩçIJĨ
    0.06
    åŃĺçļĦ
    0.06
    chsel
    0.06
    æ¸ħ鼶
    0.06
    Activations Density 0.017%

    No Known Activations