© 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. 28992
    Prev
    Next
    INDEX
    Explanations

    numerical sequences and identifiers

    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
    unkt
    -0.07
    angan
    -0.07
    åįĬ
    -0.07
    agnes
    -0.06
    çī¹
    -0.06
    çħ§
    -0.06
    kal
    -0.06
    åIJ§
    -0.06
    pet
    -0.06
    shade
    -0.06
    POSITIVE LOGITS
    менов
    0.08
    顾åIJįæĢĿä¹ī
    0.08
    uesa
    0.07
    .Typed
    0.07
    riad
    0.07
    avity
    0.07
    oten
    0.07
     enten
    0.07
    ä¸įè§ģ
    0.06
    otas
    0.06
    Activations Density 0.013%

    No Known Activations