© 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. 33544
    Prev
    Next
    INDEX
    Explanations

    updating/updated data

    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
    /her
    -0.11
    atina
    -0.10
    以赴
    -0.09
    atical
    -0.09
    onne
    -0.09
     ÙĪراء
    -0.08
    quê
    -0.08
    schaft
    -0.08
    ët
    -0.08
    eric
    -0.08
    POSITIVE LOGITS
    æį¢ä»£
    0.15
    OrCreate
    0.09
    /update
    0.09
    /down
    0.08
    /add
    0.08
    /delete
    0.08
    /up
    0.08
    /rem
    0.08
    (update
    0.07
    åĴĮå®ĮåĸĦ
    0.07
    Activations Density 0.066%

    No Known Activations