© 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. 38523
    Prev
    Next
    INDEX
    Explanations

    template, DNA, or RNA sequences

    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
    attrib
    -0.08
     Roos
    -0.08
    apan
    -0.08
    mtree
    -0.08
    arro
    -0.08
    è´§åĪ°
    -0.08
    áĥIJáĥĽ
    -0.08
    ventus
    -0.08
    apkan
    -0.08
    cef
    -0.07
    POSITIVE LOGITS
     waarop
    0.07
    ież
    0.07
     prom
    0.07
     guiding
    0.07
    åĴĮ缮æłĩ
    0.07
    uide
    0.06
     during
    0.06
     guidance
    0.06
    encoding
    0.06
     substrate
    0.06
    Activations Density 0.014%

    No Known Activations