© 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. 34224
    Prev
    Next
    INDEX
    Explanations

    fold, composition, one, 0

    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
    agne
    -0.07
    |[
    -0.07
    ç£
    -0.07
    dv
    -0.06
    ernet
    -0.06
    ired
    -0.06
    Ïģιθ
    -0.06
    ÙĬØ«
    -0.06
    åĢ
    -0.06
    onian
    -0.06
    POSITIVE LOGITS
    å´İ
    0.08
    occhi
    0.08
    .dat
    0.07
    cking
    0.07
    ãĥIJãĥ³ãĤ¯
    0.07
    ponder
    0.07
    çīĪæĿĥ声æĺİ
    0.07
    éĩĮäºļ
    0.07
     contempl
    0.07
    Ports
    0.07
    Activations Density 0.012%

    No Known Activations