© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15625
    Prev
    Next
    INDEX
    Explanations

    say "password"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    沱
    -17.50
    emit
    -16.88
     emit
    -16.63
     Burl
    -16.50
     Emit
    -16.38
    ARB
    -16.13
    �
    -16.00
     öl
    -15.94
     PROCUREMENT
    -15.88
    	emit
    -15.69
    POSITIVE LOGITS
     password
    43.75
     passwords
    42.00
     Password
    40.50
    password
    40.00
    密码
    39.50
    Password
    38.75
    .Password
    38.00
    	password
    37.75
    .password
    36.25
    =password
    36.25
    Activations Density 0.126%

    No Known Activations