© 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. 9888
    Prev
    Next
    INDEX
    Explanations

    cultural aspects and modifications

    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
    å¡ĹãĤĬ
    -0.06
    ol
    -0.06
    é¦ĸåħĪ
    -0.06
    ç»®
    -0.06
    oes
    -0.06
     zwar
    -0.06
     Sej
    -0.06
    stit
    -0.06
     enim
    -0.06
    CompleteListener
    -0.06
    POSITIVE LOGITS
    ancode
    0.07
    ambat
    0.07
    yaç
    0.07
    antul
    0.07
    åĽ½åħ¬
    0.07
    éĢģæĪij
    0.06
    sent
    0.06
    ä¸įéĢı
    0.06
    yty
    0.06
    ·¸
    0.06
    Activations Density 0.144%

    No Known Activations