© 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. 27456
    Prev
    Next
    INDEX
    Explanations

    angular properties and measurements

    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
    ëģĶ
    -0.10
    -être
    -0.10
    ek
    -0.10
    翼翼
    -0.10
    <|box_end|>
    -0.09
    jÅ¡ÃŃ
    -0.09
    åĢijçļĦ
    -0.09
    imizer
    -0.09
    ï¾ŀ
    -0.09
    earch
    -0.08
    POSITIVE LOGITS
    ly
    0.10
    s
    0.10
    ity
    0.09
    idad
    0.09
    ities
    0.09
    sak
    0.08
    ic
    0.08
    ar
    0.08
    ा
    0.08
    al
    0.08
    Activations Density 0.013%

    No Known Activations