© 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. 3675
    Prev
    Next
    INDEX
    Explanations

    ManhattanConnectionRouter, this.id

    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
    aley
    -0.07
    åįİé¾Ļ
    -0.07
    åĵį亮
    -0.07
    åħ¨
    -0.07
    ¤
    -0.07
    èıģ
    -0.06
    ¯
    -0.06
    åĩ¡
    -0.06
    à¸ĵะ
    -0.06
    ä½ļ
    -0.06
    POSITIVE LOGITS
    ÑĢÑĥжи
    0.08
    uto
    0.07
    æľ±
    0.07
    teni
    0.07
     (“
    0.07
    dez
    0.07
    isure
    0.07
    formatter
    0.07
    zat
    0.07
    (SS
    0.07
    Activations Density 0.058%

    No Known Activations