© 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. 19286
    Prev
    Next
    INDEX
    Explanations

    let/alpha expressions

    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
    ç»°
    -0.07
    éĩij马
    -0.07
    hec
    -0.07
    æħµ
    -0.07
    quo
    -0.07
    ARGIN
    -0.07
    itle
    -0.07
    rouw
    -0.07
    ERGE
    -0.07
    .Slice
    -0.06
    POSITIVE LOGITS
     autod
    0.07
    å¸Ĩ
    0.07
     kaz
    0.06
    ç®ĢåįķçļĦ
    0.06
    å¥½åľ¨
    0.06
    atina
    0.06
    åĦ
    0.06
    AuthProvider
    0.06
    èĩªæݧ
    0.06
    éĽģ
    0.06
    Activations Density 0.028%

    No Known Activations