© 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. 21470
    Prev
    Next
    INDEX
    Explanations

    class A () or B ()

    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
    gue
    -0.07
    åŃIJéĩĮ
    -0.07
    å°Ķåħĭ
    -0.07
    onto
    -0.06
    zd
    -0.06
    æģŃ
    -0.06
    vel
    -0.06
    èĢĮèµ°
    -0.06
    oland
    -0.06
    å·²ä¹ħ
    -0.06
    POSITIVE LOGITS
    queta
    0.08
     undisclosed
    0.07
    aData
    0.07
    anvas
    0.07
    estern
    0.06
    arna
    0.06
    oplast
    0.06
    _EXTERNAL
    0.06
    .defer
    0.06
     dedi
    0.06
    Activations Density 0.001%

    No Known Activations