© 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. 30898
    Prev
    Next
    INDEX
    Explanations

    IR spectra analysis

    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
    .nlm
    -0.09
    èİĬ
    -0.08
     Annonce
    -0.08
    edImage
    -0.08
    AsString
    -0.08
    <quote
    -0.08
    NotFoundError
    -0.08
    ighbor
    -0.08
    _QMARK
    -0.08
    heiten
    -0.08
    POSITIVE LOGITS
    oros
    0.08
     evidence
    0.08
    åĴĮç½ij绾
    0.07
    Kit
    0.07
    ian
    0.07
    /X
    0.07
    nasium
    0.07
     findings
    0.07
    è¯ģå®ŀ
    0.06
    /
    0.06
    Activations Density 0.226%

    No Known Activations