© 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. 22048
    Prev
    Next
    INDEX
    Explanations

    authentication digits

    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
    Õ
    -0.07
    -0.07
    人æĦı
    -0.07
    illot
    -0.07
    åIJ¾
    -0.07
    èĩªå·±è¢«
    -0.07
    èĩªå·±
    -0.06
    -ish
    -0.06
    /her
    -0.06
    SharedPointer
    -0.06
    POSITIVE LOGITS
    Ø©
    0.09
    翼翼
    0.08
    ecte
    0.08
    entication
    0.08
    tribu
    0.07
    æľīäºĭ
    0.07
    midd
    0.07
    å¾ģéĢĶ
    0.07
    stances
    0.07
    enticate
    0.07
    Activations Density 0.022%

    No Known Activations