© 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. 21715
    Prev
    Next
    INDEX
    Explanations

    inflation or influenza

    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
    INGS
    -0.08
    «
    -0.08
    lings
    -0.08
    UGIN
    -0.08
    çݯå¢ĥä¼ĺç¾İ
    -0.08
    mani
    -0.08
    itches
    -0.07
    æķ°éĩıæľīéĻIJ
    -0.07
    abouts
    -0.07
    æĪijè¦ģæĬķè¯ī
    -0.07
    POSITIVE LOGITS
    flation
    0.10
    alz
    0.08
    ary
    0.08
    çİĩçļĦ
    0.08
    çĨ
    0.08
    çİĩ
    0.08
     rate
    0.08
     inflation
    0.08
    åĬłéĢŁ
    0.07
    -rate
    0.07
    Activations Density 0.005%

    No Known Activations