© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 64044
    Prev
    Next
    INDEX
    Explanations

    N/P sequencing or distribution

    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
    ehan
    -0.08
    æľ¬ç½ij
    -0.08
    ambu
    -0.08
     widest
    -0.08
    cato
    -0.07
    eron
    -0.07
    ç¦ıçĶ°
    -0.07
    .Failure
    -0.07
    大åħ³
    -0.07
    edad
    -0.07
    POSITIVE LOGITS
    å®ŀéªĮ
    0.08
    å®ŀéªĮä¸Ń
    0.08
    è®©ä½łä»¬
    0.07
    åħĭéĩĮ
    0.07
     indict
    0.07
     radio
    0.07
     experiment
    0.07
    empel
    0.07
     DNA
    0.07
     unfit
    0.07
    Activations Density 0.001%

    No Known Activations