© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 13990
    Prev
    Next
    INDEX
    Explanations

    say label

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

    No Comments

    Negative Logits
    _grid
    -16.63
    ParameterValue
    -15.94
     grid
    -15.75
    价值
    -15.56
    Father
    -15.50
     Grid
    -15.44
    warz
    -15.31
    ipple
    -15.25
     paw
    -15.19
    :value
    -15.13
    POSITIVE LOGITS
    ABEL
    18.63
     label
    18.50
    ,label
    17.88
    [label
    17.25
    (Label
    17.13
    Label
    17.13
     LABEL
    16.88
    技能培训
    16.75
     Label
    16.38
     special
    16.00
    Activations Density 0.307%

    No Known Activations