© 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. 34516
    Prev
    Next
    INDEX
    Explanations

    description of lived experience or background

    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
    ÑĢаÑĤа
    -0.08
    éĽªæ¢¨
    -0.08
    vertime
    -0.08
     impactful
    -0.08
     Rihanna
    -0.07
     millennials
    -0.07
    enuity
    -0.07
    quo
    -0.07
     Osama
    -0.07
    inten
    -0.07
    POSITIVE LOGITS
     assorted
    0.07
     pom
    0.07
    å½ĵ天ä¸ĭåįĪ
    0.07
    åıĪä¸Ģ个
    0.07
     p
    0.07
     whatever
    0.06
     ro
    0.06
    -and
    0.06
     bo
    0.06
    äºĨ两个
    0.06
    Activations Density 0.102%

    No Known Activations