© 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. 50150
    Prev
    Next
    INDEX
    Explanations

    Url patterns

    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
    å¾·æĻº
    -0.08
    _PROP
    -0.07
     [])
    -0.07
     .=
    -0.07
    riz
    -0.07
    天价
    -0.07
    getTable
    -0.07
    ä¸įèµ°
    -0.07
    /generated
    -0.07
    []"
    -0.07
    POSITIVE LOGITS
    å¾®
    0.08
    rodom
    0.08
    ToStr
    0.07
     pel
    0.07
    åIJŀ
    0.06
     Pel
    0.06
    çĸı
    0.06
    pel
    0.06
    å¸ĥ
    0.06
    toh
    0.06
    Activations Density 0.061%

    No Known Activations