© 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. 28729
    Prev
    Next
    INDEX
    Explanations

    style attribute

    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
    uset
    -0.09
    shaw
    -0.08
    untas
    -0.08
    ataka
    -0.08
    äºĨä¸Ģè·³
    -0.08
    ترÙĨت
    -0.08
    itol
    -0.08
    åĭĿè²ł
    -0.08
    adak
    -0.08
    å·¥ä¸ļ大åѦ
    -0.08
    POSITIVE LOGITS
    ingly
    0.07
    urf
    0.06
    ungs
    0.06
    ategic
    0.06
    er
    0.06
    utdown
    0.06
    ered
    0.06
    ings
    0.06
    yyyy
    0.06
     purpose
    0.06
    Activations Density 0.020%

    No Known Activations