© 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. 33857
    Prev
    Next
    INDEX
    Explanations

    original author

    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
    etro
    -0.11
    andar
    -0.08
    .amazonaws
    -0.08
    acking
    -0.08
    اء
    -0.08
    ett
    -0.08
    ouse
    -0.07
    缸åºĶçļĦ
    -0.07
    Úĺ
    -0.07
    edly
    -0.07
    POSITIVE LOGITS
    ity
    0.15
    ness
    0.12
    ation
    0.11
    /original
    0.10
     vẹn
    0.10
    heid
    0.09
    keit
    0.09
    ized
    0.09
    inition
    0.08
    iecz
    0.08
    Activations Density 0.023%

    No Known Activations