© 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. 20024
    Prev
    Next
    INDEX
    Explanations

    energy units (GeV, TeV)

    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
    aire
    -0.08
    ural
    -0.08
    иÑħ
    -0.07
    ivit
    -0.07
    ych
    -0.07
    ¥
    -0.07
    éĿ¢ç§¯è¾¾
    -0.07
    ارÙĩ
    -0.07
    age
    -0.07
    Collapsed
    -0.07
    POSITIVE LOGITS
    ized
    0.07
     spent
    0.06
    ãĥ³
    0.06
    omorphic
    0.06
    IZES
    0.06
     ëĦĺëĬĶ
    0.06
    estra
    0.06
    æĥ³äºĨè§£æĽ´å¤ļ
    0.06
    resent
    0.06
    以ä¸ĭ
    0.06
    Activations Density 0.002%

    No Known Activations