© 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. 63255
    Prev
    Next
    INDEX
    Explanations

    unique identification fingerprint profiles

    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
    ulen
    -0.07
    æīĺ
    -0.07
    cev
    -0.07
    aru
    -0.07
    coop
    -0.07
    çī§
    -0.07
    è¨Ĺ
    -0.06
    .defer
    -0.06
    -controller
    -0.06
    æĶ¹ä¸º
    -0.06
    POSITIVE LOGITS
     иденÑĤиÑĦика
    0.14
     identity
    0.13
    çĭ¬ä¸ĢæĹłäºĮçļĦ
    0.13
     uniqueness
    0.12
     fingerprint
    0.12
     unique
    0.12
    è¯ĨåĪ«
    0.12
     fingerprints
    0.12
     иденÑĤиÑĦ
    0.12
    identification
    0.12
    Activations Density 0.104%

    No Known Activations