© 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. 19655
    Prev
    Next
    INDEX
    Explanations

    tree levels, layers, or center alignment

    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
    boli
    -0.08
    ijker
    -0.08
    stein
    -0.08
    StackTrace
    -0.07
    ä¹īåĭĩ
    -0.07
    çºĸ
    -0.07
    çĸµ
    -0.07
    коÑĤ
    -0.07
    .CreateInstance
    -0.07
    åīĶ
    -0.07
    POSITIVE LOGITS
     Separator
    0.08
    ukul
    0.07
    ãģĶãģ¨
    0.07
    -wise
    0.06
    _horizontal
    0.06
    gre
    0.06
    åĪĨéļĶ
    0.06
    zis
    0.06
    -padding
    0.06
    Å¡Äį
    0.06
    Activations Density 0.006%

    No Known Activations