© 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. 16659
    Prev
    Next
    INDEX
    Explanations

    suffix -ic

    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
    ingly
    -0.09
    Ø©
    -0.09
    aus
    -0.07
    edly
    -0.07
    er
    -0.07
    i
    -0.07
    ed
    -0.06
    +xml
    -0.06
    ãĤº
    -0.06
    èµĦ
    -0.06
    POSITIVE LOGITS
    ited
    0.09
    ELY
    0.08
    impa
    0.08
    eshire
    0.08
    kej
    0.08
    izzi
    0.08
    СТЬ
    0.08
    idad
    0.08
    iting
    0.08
    idades
    0.08
    Activations Density 0.002%

    No Known Activations