© 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. 38718
    Prev
    Next
    INDEX
    Explanations

    hyperechogenic, cumulatively, nostalrius

    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
    Ùĩ
    -0.34
    ãĥ³
    -0.24
    en
    -0.24
    es
    -0.21
    an
    -0.19
    u
    -0.19
    ed
    -0.18
    er
    -0.18
    åľ¨
    -0.16
    i
    -0.15
    POSITIVE LOGITS
    ness
    0.17
    tures
    0.16
    ificates
    0.14
    onical
    0.14
    apsed
    0.14
    -être
    0.13
    hood
    0.12
    istration
    0.12
    tedir
    0.12
    iveness
    0.12
    Activations Density 4.724%

    No Known Activations