© 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. 50730
    Prev
    Next
    INDEX
    Explanations

    focal length

    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
     tro
    -0.07
    æĶ¾å¿ĥçļĦ
    -0.07
    çī²
    -0.07
    é¢ij次
    -0.07
    éĩįçļĦ
    -0.07
    unga
    -0.07
    liv
    -0.07
    éĩį
    -0.06
     Variables
    -0.06
    жено
    -0.06
    POSITIVE LOGITS
    caria
    0.08
     length
    0.07
    å¾ĪçŁŃ
    0.07
    -length
    0.07
    空头
    0.07
    SHORT
    0.07
    éķ¿åº¦
    0.07
     ingy
    0.07
    çĦ¦è·Ŀ
    0.07
    aleza
    0.07
    Activations Density 0.001%

    No Known Activations