© 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. 28261
    Prev
    Next
    INDEX
    Explanations

    numbers in lists or dictionaries

    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
     Shed
    -0.07
     shed
    -0.07
     Earn
    -0.06
     Chat
    -0.06
    iber
    -0.06
     shedding
    -0.06
    vr
    -0.06
    abl
    -0.06
    _PROPERTY
    -0.06
    vel
    -0.06
    POSITIVE LOGITS
    arsed
    0.10
    erima
    0.10
    aisu
    0.10
     Kolej
    0.08
    enance
    0.08
    repid
    0.08
    enal
    0.08
    rawer
    0.08
    anguages
    0.08
    çĴ¨
    0.07
    Activations Density 0.005%

    No Known Activations