© 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. 2964
    Prev
    Next
    INDEX
    Explanations

    repo

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

    No Comments

    Negative Logits
    Civil
    -18.63
    文明
    -18.25
    civil
    -17.00
     Civil
    -16.88
    udes
    -16.50
     Eth
    -16.25
     civil
    -15.50
    .segments
    -15.25
    ethyl
    -15.25
    imate
    -15.25
    POSITIVE LOGITS
     repo
    62.25
     Repo
    60.25
    repo
    58.50
    Repo
    58.00
    (repo
    56.00
    _repo
    51.75
    .repo
    50.00
    _REPO
    45.25
     repos
    44.50
    repos
    39.50
    Activations Density 0.024%

    No Known Activations