© 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. 10084
    Prev
    Next
    INDEX
    Explanations

    when or if logic

    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
    heimer
    -0.08
     Ghi
    -0.07
    anon
    -0.07
    ÏĪε
    -0.07
    :request
    -0.07
    ÏĢί
    -0.06
    Ñģени
    -0.06
    dcc
    -0.06
    brem
    -0.06
    etag
    -0.06
    POSITIVE LOGITS
    orem
    0.08
    åIJİèĢħ
    0.07
    )],
    0.07
     _______,
    0.07
    >>,
    0.07
    以对
    0.07
    设æ³ķ
    0.06
    piring
    0.06
    åīįèĢħ
    0.06
    )][
    0.06
    Activations Density 0.025%

    No Known Activations