© 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. 64724
    Prev
    Next
    INDEX
    Explanations

    URLs and URIs

    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
    å¡ijéĢł
    -0.08
    поÑĢа
    -0.06
    dak
    -0.06
    æĬĬä»ĸçļĦ
    -0.06
    quisite
    -0.06
    åĭĩ
    -0.06
    laÄį
    -0.06
    =Integer
    -0.06
    surname
    -0.06
    kowski
    -0.06
    POSITIVE LOGITS
    .href
    0.11
    .url
    0.10
    URL
    0.10
    è·¯å¾Ħ
    0.10
     URL
    0.10
     URLs
    0.10
    _urls
    0.09
     Url
    0.09
    ç½ijåĿĢ
    0.09
    網åĿĢ
    0.09
    Activations Density 0.483%

    No Known Activations