© 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. 42376
    Prev
    Next
    INDEX
    Explanations

    shapes each other

    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
    并å¤Ħ
    -0.08
    รร
    -0.07
    garan
    -0.07
     koll
    -0.07
    macher
    -0.07
    åĨįæİ¥åĨį
    -0.07
     offentlig
    -0.07
    _RW
    -0.07
    .Utility
    -0.07
    heits
    -0.07
    POSITIVE LOGITS
    åıįè¿ĩæĿ¥
    0.15
     vice
    0.12
     recip
    0.12
    缸äºĴ
    0.11
    å½¼æѤ
    0.11
    åıį
    0.10
     mutual
    0.10
     Conversely
    0.10
    mut
    0.10
     mutually
    0.10
    Activations Density 0.079%

    No Known Activations