© 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. 18905
    Prev
    Next
    INDEX
    Explanations

    SQL keywords and structured 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
    uo
    -0.08
    uhn
    -0.07
    ohn
    -0.06
    ushima
    -0.06
    oron
    -0.06
    o
    -0.06
    ake
    -0.06
    Nx
    -0.06
    fs
    -0.06
     rst
    -0.05
    POSITIVE LOGITS
    htdocs
    0.08
    殿
    0.08
    estig
    0.07
    以赴
    0.07
    ινή
    0.07
    estin
    0.07
    langs
    0.07
    astique
    0.07
    ãģĽãĤĵ
    0.07
    erspective
    0.07
    Activations Density 0.025%

    No Known Activations