© 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. 29249
    Prev
    Next
    INDEX
    Explanations

    empty content

    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
    ลฯ
    -0.10
    inally
    -0.09
    althy
    -0.09
    leps
    -0.08
    estro
    -0.08
    thouse
    -0.08
    urally
    -0.08
    UnderTest
    -0.08
    tright
    -0.08
    lez
    -0.08
    POSITIVE LOGITS
    ness
    0.11
    èį¡èį¡
    0.11
    -handed
    0.09
    -hearted
    0.09
    -ish
    0.08
    ish
    0.08
    -headed
    0.08
    NESS
    0.07
    one
    0.07
    erton
    0.07
    Activations Density 0.022%

    No Known Activations