© 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. 57977
    Prev
    Next
    INDEX
    Explanations

    officers of, names of people

    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
    åħ¬é¦Ĩ
    -0.07
    )':
    -0.07
     برابر
    -0.07
    åİŁåĪĻä¸Ĭ
    -0.07
    اÙĨØ´
    -0.06
    érée
    -0.06
    æľŁä¸Ń
    -0.06
    érées
    -0.06
    )":
    -0.06
    utin
    -0.06
    POSITIVE LOGITS
    lew
    0.07
    ĩ´
    0.07
    assis
    0.07
    è¡·
    0.07
    chenk
    0.07
    juh
    0.07
    omite
    0.06
    iefert
    0.06
    spro
    0.06
    å°Ķé¡¿
    0.06
    Activations Density 0.010%

    No Known Activations