© 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. 18350
    Prev
    Next
    INDEX
    Explanations

    not serve or cannot serve

    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
    ¤íĹ
    -0.08
    èijĨ
    -0.08
    æŶä¸ĭ
    -0.08
    antly
    -0.08
    æ¯Ķè¼ĥçļĦ
    -0.07
     specta
    -0.07
    erais
    -0.07
    <|repo_name|>
    -0.07
    #
    -0.07
    amat
    -0.07
    POSITIVE LOGITS
    大人
    0.07
    åįģåĽĽ
    0.06
    ennis
    0.06
     ↵
    0.06
    วัà¸ķ
    0.06
    æį²
    0.06
    ↵                    ↵
    0.05
    ak
    0.05
    åįģä¸ī
    0.05
    ww
    0.05
    Activations Density 0.001%

    No Known Activations