© 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. 63991
    Prev
    Next
    INDEX
    Explanations

    formulate and formulation

    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
    wards
    -0.10
    สà¸Ļิà¸Ĺ
    -0.10
    falls
    -0.08
    mals
    -0.08
    irk
    -0.08
    fold
    -0.08
    ÃŃfica
    -0.08
    ylon
    -0.08
    виÑĩ
    -0.08
    imal
    -0.08
    POSITIVE LOGITS
     ulang
    0.10
    asikan
    0.08
    ä¸įæ¸ħ
    0.08
    otion
    0.08
    atter
    0.07
    gebung
    0.07
    useum
    0.07
    cular
    0.07
    pjes
    0.07
    ulates
    0.07
    Activations Density 0.007%

    No Known Activations