© 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. 1083
    Prev
    Next
    INDEX
    Explanations

    matrix and array structures

    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
    akis
    -0.06
    æłijä¸ĬçļĦ
    -0.06
     ?.
    -0.06
     abs
    -0.06
    cept
    -0.06
    onia
    -0.05
     relevant
    -0.05
    akon
    -0.05
     bit
    -0.05
    âĢ¦ãĢĤ
    -0.05
    POSITIVE LOGITS
    ä½¼
    0.09
     Luh
    0.09
    iland
    0.08
    گار
    0.08
    Stamped
    0.08
    oleÄį
    0.08
    اÙħا
    0.07
     flexibil
    0.07
    öö
    0.07
    _NR
    0.07
    Activations Density 0.005%

    No Known Activations