© 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. 32268
    Prev
    Next
    INDEX
    Explanations

    css comment start

    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
    çľ¼åīįçļĦ
    -0.07
    窪
    -0.07
    rox
    -0.07
    áĥĵáĥIJ
    -0.07
    ->[
    -0.07
    nyi
    -0.07
    Ø´ÙĪ
    -0.07
    arena
    -0.07
    icali
    -0.07
    è°Ľ
    -0.07
    POSITIVE LOGITS
    夫
    0.06
    ToF
    0.06
    å±ħ
    0.06
    erei
    0.06
    -wrap
    0.06
    innen
    0.06
    /*
    0.06
    ovor
    0.06
    Gray
    0.06
    egan
    0.06
    Activations Density 0.027%

    No Known Activations