© 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. 60173
    Prev
    Next
    INDEX
    Explanations

    _DEF, _ing

    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
    OCO
    -0.08
    æ¯ı天æĹ©ä¸Ĭ
    -0.08
    .ascii
    -0.08
    ItemType
    -0.07
    leh
    -0.07
    amus
    -0.07
    ihat
    -0.07
    OnInit
    -0.07
    abouts
    -0.07
    áĥIJáĥ®
    -0.07
    POSITIVE LOGITS
    å¼¹
    0.07
    poz
    0.06
    å®ķ
    0.06
    ä¹Ŀä¹Ŀ
    0.06
     pops
    0.06
    egas
    0.06
    åĮĸçī©
    0.06
    æ¥ļ天
    0.06
    -du
    0.06
    å¥Īä½ķ
    0.06
    Activations Density 0.011%

    No Known Activations