© 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. 34230
    Prev
    Next
    INDEX
    Explanations

    inside structures or containers

    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
    å·¥ä½ľä¸ĬçļĦ
    -0.07
    upply
    -0.07
    ubectl
    -0.07
    rzy
    -0.07
    ulers
    -0.06
    ÅĻi
    -0.06
    éģł
    -0.06
    楼ä¸Ĭ
    -0.06
    íĥĪ
    -0.06
    xffffffff
    -0.06
    POSITIVE LOGITS
     ÙĪبÙĬÙĨ
    0.13
    halb
    0.11
     cadrul
    0.10
     confines
    0.09
    ewnÄħtrz
    0.09
     midst
    0.09
    åĨħè¿Ľè¡Į
    0.09
    /out
    0.08
    Within
    0.08
     sebou
    0.08
    Activations Density 0.137%

    No Known Activations