© 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. 24775
    Prev
    Next
    INDEX
    Explanations

    impedances or impedance

    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
    é¢ł
    -0.07
    åıijçļĦ
    -0.06
     cess
    -0.06
    urang
    -0.06
    沸
    -0.06
    aptor
    -0.06
    yel
    -0.06
    æİīçļĦ
    -0.06
    åĩºçĶŁçļĦ
    -0.06
    egni
    -0.06
    POSITIVE LOGITS
    stub
    0.08
    çī¹æĢ§çļĦ
    0.08
    éĺ»æĬĹ
    0.08
    箫
    0.08
    INLINE
    0.07
    tron
    0.07
    ä¸ĩåĽ½
    0.07
     resist
    0.07
    gnore
    0.07
    Ľ
    0.07
    Activations Density 0.003%

    No Known Activations