© 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. 8384
    Prev
    Next
    INDEX
    Explanations

    cryopreservation and frozen materials

    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
    cioni
    -0.08
    _colors
    -0.07
     caus
    -0.07
    ajar
    -0.07
    sst
    -0.07
     Luh
    -0.07
    鼨åIJİ
    -0.07
    heen
    -0.07
     Cros
    -0.07
    rss
    -0.07
    POSITIVE LOGITS
     thaw
    0.10
    åĨ°
    0.09
    åĨ·åĨ»
    0.09
     ice
    0.09
    freeze
    0.08
    æ°·
    0.08
    解åĨ»
    0.08
     Ice
    0.08
    åĨ°åĨ»
    0.08
     freeze
    0.07
    Activations Density 0.029%

    No Known Activations