© 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. 15657
    Prev
    Next
    INDEX
    Explanations

    iOS 13 and macOS 10.15

    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
    agus
    -0.08
    ä¸Ģ转
    -0.07
    çļĦä¸įèī¯
    -0.07
    otov
    -0.07
    inger
    -0.07
    eningen
    -0.07
    称为
    -0.07
    kuš
    -0.07
     instability
    -0.07
    agnost
    -0.07
    POSITIVE LOGITS
     tramp
    0.07
    REEN
    0.07
    è°·éĽ¨
    0.06
    spy
    0.06
    *)((
    0.06
    upp
    0.06
    .").
    0.06
    ALO
    0.06
    çĤ¬
    0.06
    FieldValue
    0.06
    Activations Density 0.007%

    No Known Activations