© 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. 38805
    Prev
    Next
    INDEX
    Explanations

    wavelengths or energies in nm or GeV

    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
    STREAM
    -0.06
    á»Ŀ
    -0.06
     (
    -0.06
    æ°Ķé¦ģ
    -0.06
    anz
    -0.06
    ä¸įå·®
    -0.06
     mar
    -0.06
    èĻı
    -0.06
    -0.05
    çĹ´
    -0.05
    POSITIVE LOGITS
    èĮī
    0.09
    ycz
    0.09
    fach
    0.09
     emitting
    0.08
    é¢ĦéĢī
    0.08
    szy
    0.08
    ήμε
    0.08
    cza
    0.08
    hurst
    0.08
    å°Ķ夫
    0.08
    Activations Density 0.201%

    No Known Activations