© 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. 23887
    Prev
    Next
    INDEX
    Explanations

    closing bracket `]`

    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
    ../../../
    -0.10
    åĮªæµħ
    -0.10
    ation
    -0.09
    ajer
    -0.08
    çļĻ
    -0.08
    entication
    -0.08
    rial
    -0.08
    .FILES
    -0.08
    ence
    -0.07
     akik
    -0.07
    POSITIVE LOGITS
    sung
    0.09
    edula
    0.08
    spro
    0.08
    saf
    0.07
    ught
    0.07
    sen
    0.07
    itional
    0.07
    sse
    0.07
    schirm
    0.07
    sch
    0.07
    Activations Density 0.015%

    No Known Activations