© 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. 3837
    Prev
    Next
    INDEX
    Explanations

    verbs indicating action or process

    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
    adem
    -0.08
     importantly
    -0.07
     moreover
    -0.07
    panse
    -0.07
    _hierarchy
    -0.07
    -placeholder
    -0.07
     egz
    -0.07
    usen
    -0.06
    odable
    -0.06
    esis
    -0.06
    POSITIVE LOGITS
     terlebih
    0.08
    éĢĤå½ĵçļĦ
    0.08
     directly
    0.08
     từng
    0.08
    åīįåħĪ
    0.07
    缴æİ¥ä»İ
    0.07
     painstaking
    0.07
    导
    0.07
     directement
    0.07
    anco
    0.07
    Activations Density 0.029%

    No Known Activations