© 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. 2160
    Prev
    Next
    INDEX
    Explanations

    delta, Page, days

    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
    ehme
    -0.07
    ÅĤos
    -0.06
    ä¸Ńå±±
    -0.06
     (“
    -0.06
    oso
    -0.06
    inkin
    -0.06
    oo
    -0.06
     compreh
    -0.06
     ("
    -0.06
    .mongodb
    -0.05
    POSITIVE LOGITS
    ipient
    0.08
    ÙĩاÙĨ
    0.08
    ieux
    0.07
    hea
    0.07
    Kep
    0.07
    erschaft
    0.07
    _DIP
    0.07
     ìĿĺìĽIJìĿĢ
    0.07
    aeper
    0.07
    efa
    0.07
    Activations Density 0.001%

    No Known Activations