© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14888
    Prev
    Next
    INDEX
    Explanations

    say 2

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

    No Comments

    Negative Logits
    UG
    -16.25
     THR
    -15.19
    oggles
    -15.06
     Hag
    -14.88
    uels
    -14.56
     negotiation
    -14.56
    AGR
    -14.50
    瘘
    -14.50
    珐
    -14.44
     thrust
    -14.13
    POSITIVE LOGITS
    puty
    17.50
    anter
    17.00
    anne
    15.56
    项
    15.19
    edin
    15.19
    managed
    14.31
    ichel
    14.25
    aine
    14.00
    -Identifier
    13.63
    beh
    13.56
    Activations Density 0.011%

    No Known Activations