© 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. 43222
    Prev
    Next
    INDEX
    Explanations

    "in" or "as"

    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
    çĻ¾åıĺ
    -0.07
    ÑĢÑĥжи
    -0.06
     tro
    -0.06
    vara
    -0.06
    imax
    -0.06
    _run
    -0.06
    bola
    -0.06
    blad
    -0.06
    iva
    -0.06
    лÑĮÑĦа
    -0.06
    POSITIVE LOGITS
    iap
    0.07
    СУ
    0.07
     clearTimeout
    0.07
    åIJijåħ¶
    0.07
    èĭijå°ıåĮº
    0.07
    ãm
    0.07
    _ATTRIB
    0.07
    说æĿ¥
    0.07
    elligen
    0.07
    å®ĥçļĦ
    0.07
    Activations Density 0.019%

    No Known Activations