© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48210
    Prev
    Next
    INDEX
    Explanations

    out of X

    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
     íĦ¸
    -0.07
    ao
    -0.06
    èĩ´
    -0.06
    éŀį
    -0.06
    å§ĭ
    -0.06
    åĪĽ
    -0.06
    bs
    -0.06
    ral
    -0.06
    ra
    -0.06
    dea
    -0.06
    POSITIVE LOGITS
    eschi
    0.09
     أصÙĦ
    0.09
    ymm
    0.08
    jala
    0.07
    gesch
    0.07
    ÛĮدÛĮ
    0.07
    UES
    0.07
     otherwise
    0.07
    çĻ½éĽª
    0.07
    paque
    0.07
    Activations Density 0.256%

    No Known Activations