© 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. 24041
    Prev
    Next
    INDEX
    Explanations

    magic variable

    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
    rotation
    -0.07
    yer
    -0.07
    .native
    -0.07
    鸳
    -0.07
     Rudd
    -0.07
    计ç®Ĺæľºç³»ç»Ł
    -0.07
    _processors
    -0.07
    ennes
    -0.06
    éļĽ
    -0.06
    byn
    -0.06
    POSITIVE LOGITS
     assumed
    0.10
    utel
    0.08
    åģĩ设
    0.08
     assumptions
    0.08
     assumption
    0.07
     assum
    0.07
    设å®ļ
    0.07
     assumes
    0.07
    çļĦ设置
    0.07
     assume
    0.07
    Activations Density 0.005%

    No Known Activations