© 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. 2439
    Prev
    Next
    INDEX
    Explanations

    Internet

    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
    ments
    -0.09
    TURE
    -0.08
    æ®Ĩå°½
    -0.08
    å¦Ĥå±±
    -0.07
    AllWindows
    -0.07
    chter
    -0.07
     relo
    -0.07
    Ù°
    -0.07
    ustralian
    -0.07
    们
    -0.07
    POSITIVE LOGITS
    /web
    0.08
    ä¸ĬçļĦ
    0.08
    /Web
    0.08
    inary
    0.07
    oxide
    0.07
     Internet
    0.07
     savvy
    0.07
    alia
    0.07
    bing
    0.07
    ory
    0.07
    Activations Density 0.100%

    No Known Activations