© 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. 16558
    Prev
    Next
    INDEX
    Explanations

    risk, relative comparisons, state

    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
     Pach
    -0.06
    ERO
    -0.06
    çī©æĸĻ
    -0.06
    inkin
    -0.06
    urd
    -0.06
    æıŃ
    -0.06
     disput
    -0.06
    urga
    -0.06
    ouch
    -0.06
    让对æĸ¹
    -0.06
    POSITIVE LOGITS
    çĽ¸å¯¹äºİ
    0.22
     rispetto
    0.16
    缸è¾ĥäºİ
    0.15
     compared
    0.14
     ÙĨسبت
    0.14
     relative
    0.14
    åģı离
    0.14
    relative
    0.14
     Compared
    0.14
    缸æ¯Ķ
    0.13
    Activations Density 0.210%

    No Known Activations