© 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. 23771
    Prev
    Next
    INDEX
    Explanations

    case object, type constructor

    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
    лк
    -0.07
    etra
    -0.06
    ral
    -0.06
    á»ģn
    -0.06
    åħī顾
    -0.06
     dés
    -0.06
    çĸ¯çĭĤçļĦ
    -0.06
    ä¸Ĭå²Ĺ
    -0.06
    ahari
    -0.06
    raad
    -0.06
    POSITIVE LOGITS
    (_,
    0.08
    ÙijÙī
    0.08
    åijĬçŁ¥
    0.07
    isata
    0.07
    è¯Ľä»Ļ
    0.07
    å§Ķ
    0.07
    nant
    0.07
     compac
    0.07
    orthy
    0.07
    ukas
    0.07
    Activations Density 0.024%

    No Known Activations