© 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. 39908
    Prev
    Next
    INDEX
    Explanations

    radio control

    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
    yclic
    -0.10
    vena
    -0.08
    _oid
    -0.08
    uards
    -0.08
     istim
    -0.08
    icity
    -0.08
    illah
    -0.08
    komst
    -0.08
    ulette
    -0.08
    äºĮè¯Ŀ
    -0.07
    POSITIVE LOGITS
     mini
    0.09
     glor
    0.08
    äºĨä¸Ģåľº
    0.07
    æĽ´åĥıæĺ¯
    0.07
    åįĬ个
    0.07
     rather
    0.07
    çīĪçļĦ
    0.07
    èĢĮéĿŀ
    0.07
    åıĺæĪIJäºĨä¸Ģ个
    0.07
     disguised
    0.07
    Activations Density 0.283%

    No Known Activations