© 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. 987
    Prev
    Next
    INDEX
    Explanations

    specialized variable names

    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
    sev
    -0.06
     nim
    -0.06
    رة
    -0.06
    çĤ¹æ»´
    -0.06
    uts
    -0.06
    rh
    -0.06
    iker
    -0.06
    åIJ¯
    -0.06
     pon
    -0.06
     impe
    -0.06
    POSITIVE LOGITS
    èIJĿ
    0.08
    说çļĦæĺ¯
    0.08
    cala
    0.08
    .au
    0.08
    åħĭ鼷
    0.08
    issons
    0.08
    zio
    0.08
    øj
    0.07
    综åIJĪè¿IJçĶ¨
    0.07
    дово
    0.07
    Activations Density 0.096%

    No Known Activations