© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10704
    Prev
    Next
    INDEX
    Explanations

    lifting orthogonal

    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
    ular
    -0.06
    xA
    -0.06
    omics
    -0.06
    1
    -0.06
    åıijäºĨ
    -0.06
    צ
    -0.06
    6
    -0.06
     erf
    -0.06
     prolifer
    -0.06
    aka
    -0.05
    POSITIVE LOGITS
    PRETTY
    0.09
    asih
    0.08
    /epl
    0.08
    retty
    0.08
    山头
    0.08
    éri
    0.08
     ФÑĥÑĤбо
    0.08
     Ilmais
    0.08
    баÑħ
    0.08
    ffre
    0.08
    Activations Density 0.007%

    No Known Activations