© 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. 7887
    Prev
    Next
    INDEX
    Explanations

    holographic, special, dates

    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
    -0.08
    åħ¬å®³
    -0.07
    宣åijĬ
    -0.06
    ↵↵
    -0.06
    æľº
    -0.06
    ç¤
    -0.06
     Union
    -0.06
    '
    -0.06
     mains
    -0.06
     magazine
    -0.06
    POSITIVE LOGITS
     deepest
    0.09
    µľ
    0.09
     corres
    0.09
     Khu
    0.09
    Encoded
    0.09
    Õ¥Õ½
    0.09
    ajaan
    0.08
     inz
    0.08
    üst
    0.08
    evice
    0.08
    Activations Density 0.010%

    No Known Activations