© 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. 3896
    Prev
    Next
    INDEX
    Explanations

    uniqueness or lack thereof

    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
    enzi
    -0.09
    eran
    -0.08
    itage
    -0.08
    _CHUNK
    -0.07
     Lesb
    -0.07
    INES
    -0.07
    legg
    -0.07
    亲亲
    -0.07
    ergic
    -0.07
    udan
    -0.07
    POSITIVE LOGITS
     uniqueness
    0.14
     Unique
    0.09
     unique
    0.08
     chặt
    0.08
    (unique
    0.08
    unique
    0.08
    åĶ¯ä¸Ģ
    0.08
    .Unique
    0.08
    æĥŁ
    0.08
    |unique
    0.08
    Activations Density 0.008%

    No Known Activations