© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 55979
    Prev
    Next
    INDEX
    Explanations

    integer types

    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
    rior
    -0.07
    ."]
    -0.07
    ulli
    -0.07
    "];
    -0.07
    noinspection
    -0.07
    `;
    -0.06
    '];
    -0.06
    `}
    -0.06
    "]}
    -0.06
    "].(
    -0.06
    POSITIVE LOGITS
    istere
    0.08
     {}:
    0.08
    ç½ijç«Ļé¦ĸ页
    0.08
    æĺĬ
    0.07
    unas
    0.07
    OrCreate
    0.07
    almaz
    0.07
    bou
    0.07
    baka
    0.07
    queta
    0.06
    Activations Density 0.052%

    No Known Activations