© 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. 3994
    Prev
    Next
    INDEX
    Explanations

    gravity, samba, Government

    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
     Piper
    -0.07
    ÑĨо
    -0.06
    evas
    -0.06
    imenta
    -0.06
    iage
    -0.06
    uilt
    -0.06
     OSD
    -0.06
    etrie
    -0.06
    ciano
    -0.06
     Rudd
    -0.06
    POSITIVE LOGITS
    åij³
    0.08
    ESO
    0.08
    å¼ķ
    0.08
    grav
    0.08
    dyn
    0.08
    iling
    0.07
    åħ¬
    0.07
    ellone
    0.07
    çĴĩ
    0.07
    à±įà°µ
    0.07
    Activations Density 0.001%

    No Known Activations