© 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. 2305
    Prev
    Next
    INDEX
    Explanations

    property

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

    No Comments

    Negative Logits
    Cons
    -19.00
     Ser
    -18.50
    ser
    -18.25
    -cons
    -18.13
     Cons
    -17.88
     cons
    -17.63
    cons
    -17.63
     ser
    -17.63
    段
    -17.50
    (segment
    -17.25
    POSITIVE LOGITS
     prop
    50.75
     Prop
    49.25
    (prop
    48.00
    prop
    47.75
    房产
    46.50
     props
    44.75
    [prop
    44.50
    Prop
    44.25
    _prop
    43.50
    -prop
    43.00
    Activations Density 0.021%

    No Known Activations