© 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. 45594
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    heb
    -0.06
    رت
    -0.06
    deb
    -0.06
     suggest
    -0.06
    سÙĩ
    -0.06
    cule
    -0.06
    ibo
    -0.06
    :not
    -0.06
     Bedford
    -0.05
    ily
    -0.05
    POSITIVE LOGITS
    alent
    0.09
    ï¼Ĭï¼Ĭï¼Ĭï¼Ĭï¼Ĭï¼Ĭï¼Ĭï¼Ĭ
    0.08
    èĦ
    0.08
    .wr
    0.07
    laces
    0.07
    ç»ıçIJĨæĭĽèģĺ
    0.07
    usher
    0.07
     CAUSED
    0.07
    åħ¶å®ĥåªĴä½ĵ
    0.07
    çons
    0.07
    Activations Density 0.476%

    No Known Activations

    This feature has no known activations.