© 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. 42418
    Prev
    Next
    INDEX
    Explanations

    key-value pairs

    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
    Ùī
    -0.07
     Istr
    -0.07
     inplace
    -0.07
    μÏĢ
    -0.07
    åı¯ä»¥æĽ´
    -0.07
    以å¾ħ
    -0.07
    istra
    -0.06
    æīĵå®Į
    -0.06
    ább
    -0.06
    åľ°ä¸ĬçļĦ
    -0.06
    POSITIVE LOGITS
    ç±»åŀĭ为
    0.07
    ä¹İ
    0.07
    lebt
    0.06
    ëį°
    0.06
    elas
    0.06
    åªĽåªĽ
    0.06
     ctype
    0.06
     name
    0.06
    bergen
    0.06
    olu
    0.06
    Activations Density 0.767%

    No Known Activations