© 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. 64901
    Prev
    Next
    INDEX
    Explanations

    password

    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
     overe
    -0.08
    andex
    -0.08
    ement
    -0.07
    Stamp
    -0.07
    AndServe
    -0.07
     derp
    -0.07
    çīĪæĿĥå±ŀäºİ
    -0.07
     ÑĢаÑģÑģе
    -0.07
    coln
    -0.07
    Injected
    -0.07
    POSITIVE LOGITS
    password
    0.12
    =password
    0.12
    å¯Ĩçłģ
    0.11
     password
    0.11
     passwords
    0.11
    /password
    0.11
    PASSWORD
    0.11
    (password
    0.11
    .Password
    0.10
     Password
    0.10
    Activations Density 0.067%

    No Known Activations