© 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. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 13989
    Prev
    Next
    INDEX
    Explanations

    say "absorb"

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

    No Comments

    Negative Logits
     projects
    -16.88
     password
    -16.88
    权重
    -16.75
    窗帘
    -16.63
    密码
    -16.63
    Projects
    -16.38
    PasswordField
    -16.25
    upro
    -16.25
    Passwords
    -16.25
     produ
    -16.25
    POSITIVE LOGITS
    派
    16.38
    支
    15.44
    _INTERFACE
    15.19
    azzi
    15.13
     absorbs
    15.06
     study
    15.00
    ắm
    14.69
     absorb
    14.56
    study
    14.06
    ingen
    14.00
    Activations Density 0.742%

    No Known Activations