© 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. 20975
    Prev
    Next
    INDEX
    Explanations

    Paradise, .org, electron, ubit

    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
    enschaft
    -0.08
     Sunder
    -0.07
    _panel
    -0.07
    潺潺
    -0.07
    åĩºåı£çļĦ
    -0.07
    èIJ½æ°´
    -0.07
    壬
    -0.07
    pez
    -0.07
    LOGGER
    -0.07
    omad
    -0.07
    POSITIVE LOGITS
    /ion
    0.08
    rita
    0.07
    第ä¸Ģ课
    0.07
    áĥIJáĥĹ
    0.07
     electron
    0.07
    é©°
    0.07
    é©°åIJį
    0.07
    ä¿Ħ
    0.07
    lon
    0.06
    çĭ±
    0.06
    Activations Density 0.001%

    No Known Activations