© 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. 46135
    Prev
    Next
    INDEX
    Explanations

    !u! tag:unity3d.com,2011:

    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
    -0.08
     bes
    -0.07
    beck
    -0.07
    tros
    -0.07
    _samples
    -0.07
    主é¢ĺåħ¬åĽŃ
    -0.06
     Champion
    -0.06
     ideal
    -0.06
    ey
    -0.06
     Bes
    -0.06
    POSITIVE LOGITS
     Detalles
    0.08
     sobres
    0.08
    ĥģ
    0.07
    è¯Ħ论åĨħ容
    0.07
    quartered
    0.07
    ÅĤugi
    0.07
    /id
    0.07
    endis
    0.07
    oplevel
    0.07
    IRD
    0.07
    Activations Density 0.062%

    No Known Activations