© 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. 46051
    Prev
    Next
    INDEX
    Explanations

    mathematical equation problem solving

    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
    åĨł
    -0.07
     Levin
    -0.07
    ambar
    -0.06
    rice
    -0.06
    rich
    -0.06
    richter
    -0.06
    å¼Ł
    -0.06
    ibe
    -0.06
    uer
    -0.06
    elib
    -0.06
    POSITIVE LOGITS
    å¾·åįİ
    0.08
    Indented
    0.08
    ưỡng
    0.07
    _HAL
    0.07
    ÑĤÑĢо
    0.07
    umat
    0.07
    åĸĶ
    0.07
    ewear
    0.07
    оÑĤ
    0.07
    åIJĥä¸ĢäºĽ
    0.07
    Activations Density 0.196%

    No Known Activations