© 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. 2218
    Prev
    Next
    INDEX
    Explanations

    say sec

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

    No Comments

    Negative Logits
    品
    -22.88
     Ant
    -17.00
    Ant
    -16.88
    ucer
    -16.75
    /pol
    -16.50
     ants
    -16.25
    _capability
    -16.13
    Capability
    -15.69
    Marg
    -15.19
     ant
    -15.13
    POSITIVE LOGITS
     Sec
    73.00
     sec
    71.50
    Sec
    71.00
    (sec
    68.00
    sec
    68.00
    _sec
    63.00
    .sec
    55.75
    /sec
    52.50
     SEC
    51.25
     secured
    50.00
    Activations Density 0.123%

    No Known Activations