© 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. 39462
    Prev
    Next
    INDEX
    Explanations

    gamma-ray energies and spectra

    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
    hé
    -0.07
    essed
    -0.07
    kina
    -0.07
    æĹłä¸į
    -0.07
     brows
    -0.07
    æ¸ł
    -0.06
    尽头
    -0.06
    ç¼ĺ
    -0.06
     instantiation
    -0.06
     Literal
    -0.06
    POSITIVE LOGITS
     radi
    0.08
    radi
    0.08
     emitted
    0.08
    æĻ®
    0.07
    repeat
    0.07
    Chance
    0.07
    åѤ
    0.07
    ืà¹īà¸Ńà¸ĩ
    0.07
     frequencies
    0.07
     Radi
    0.07
    Activations Density 0.005%

    No Known Activations