© 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. 14160
    Prev
    Next
    INDEX
    Explanations

    Imam Musa al-Sadr

    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
    åľŁçŁ³
    -0.08
    çĤİçĤİå¤ıæĹ¥
    -0.08
    ystack
    -0.07
    ëĭ¨
    -0.07
    pite
    -0.07
    ondo
    -0.07
    ør
    -0.07
    ystore
    -0.07
    undi
    -0.07
    kurat
    -0.07
    POSITIVE LOGITS
    寡
    0.07
    achs
    0.07
    alai
    0.07
    emoc
    0.06
    ungk
    0.06
    èIJ¤
    0.06
    æĥ³ä½ł
    0.06
    åĩĢ
    0.06
    enschaft
    0.06
    alha
    0.06
    Activations Density 0.123%

    No Known Activations