© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2625
    Prev
    Next
    INDEX
    Explanations

    penetration

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

    No Comments

    Negative Logits
     config
    -20.50
    config
    -19.75
     regist
    -18.88
    =config
    -17.75
     cmd
    -17.50
    cmd
    -16.50
     cert
    -16.25
    feb
    -16.13
    nty
    -16.13
    (config
    -15.81
    POSITIVE LOGITS
    渗透
    41.00
    透
    38.50
    渗
    36.00
     perme
    35.50
     perm
    31.25
    perm
    30.88
     Pen
    30.75
     Per
    30.75
     Pert
    29.63
     penetration
    29.00
    Activations Density 0.065%

    No Known Activations