© 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. 2795
    Prev
    Next
    INDEX
    Explanations

    say reservoir

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

    No Comments

    Negative Logits
    Mel
    -15.50
    mel
    -15.38
    改
    -15.38
     penal
    -15.38
    ucks
    -15.25
    SENS
    -15.13
     Cons
    -15.00
    вой
    -14.88
    cs
    -14.75
    ural
    -14.56
    POSITIVE LOGITS
     reservoir
    62.00
     Res
    51.00
    Res
    50.25
    [res
    47.50
    =res
    47.25
     RES
    47.00
    (res
    46.00
    res
    45.50
    -res
    45.00
    .res
    44.00
    Activations Density 0.046%

    No Known Activations