© 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. 26340
    Prev
    Next
    INDEX
    Explanations

    list separators and delimiters

    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
    лÑİд
    -0.07
    ht
    -0.07
    hte
    -0.06
    ë³µ
    -0.06
    _packages
    -0.06
    ames
    -0.06
    ugi
    -0.06
     within
    -0.06
    orts
    -0.06
    pec
    -0.06
    POSITIVE LOGITS
    ×ľ×ª
    0.08
    ektor
    0.08
    ellido
    0.07
     estánd
    0.07
    িয়à§ĩ
    0.07
     resultList
    0.07
    ByExample
    0.07
    ignon
    0.07
    ercial
    0.07
     absolu
    0.07
    Activations Density 0.001%

    No Known Activations