© 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. 8720
    Prev
    Next
    INDEX
    Explanations

    .springframework or .out

    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
    ery
    -0.08
    ings
    -0.08
    ements
    -0.08
    ỵ
    -0.07
    aries
    -0.07
    emuk
    -0.07
     пÑĢоÑģÑĤÑĥ
    -0.07
    ados
    -0.07
     INFORMA
    -0.07
    ubb
    -0.07
    POSITIVE LOGITS
    太éĥİ
    0.08
    饿äºĨ
    0.08
    ì²Ń
    0.07
    clipse
    0.07
    ciano
    0.07
    LOGGER
    0.07
    assistant
    0.07
    wein
    0.07
    ĥ
    0.06
    THON
    0.06
    Activations Density 0.039%

    No Known Activations