© 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. 2802
    Prev
    Next
    INDEX
    Explanations

    say retain

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

    No Comments

    Negative Logits
     Kem
    -17.50
    ра
    -16.50
    alth
    -16.25
    镜
    -16.25
    inator
    -16.13
    鏡
    -15.88
    secs
    -15.31
     sims
    -15.00
    Demo
    -14.88
    爸爸
    -14.88
    POSITIVE LOGITS
    (ret
    65.00
     Ret
    63.25
     retention
    60.25
    ret
    59.00
    Ret
    58.50
     ret
    57.00
     retained
    57.00
    -ret
    56.75
    Retention
    56.50
     retain
    56.25
    Activations Density 0.111%

    No Known Activations