© 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. 64909
    Prev
    Next
    INDEX
    Explanations

    points and totals

    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
    praw
    -0.08
    å¥
    -0.08
    bsp
    -0.07
    é¼ĵ
    -0.07
    dle
    -0.07
    ÑĤÑĥÑģ
    -0.07
    å¤ļåIJĥä¸ĢäºĽ
    -0.07
    olor
    -0.07
    ipel
    -0.07
    voy
    -0.07
    POSITIVE LOGITS
     decom
    0.07
     splits
    0.07
    ither
    0.07
    åħ¨åĮħ
    0.07
    -components
    0.07
    åĮħåIJ«äºĨ
    0.07
     combina
    0.07
    åĪĨ解
    0.07
     Decom
    0.07
     combines
    0.07
    Activations Density 0.050%

    No Known Activations