© 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. 14615
    Prev
    Next
    INDEX
    Explanations

    N/A

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

    No Comments

    Negative Logits
    aina
    -18.88
     Haj
    -18.25
    hare
    -18.00
    rabbit
    -18.00
    unny
    -17.75
    akis
    -17.75
     prisoner
    -17.25
     rabbits
    -17.13
    amba
    -17.00
    ampo
    -16.88
    POSITIVE LOGITS
    节
    20.50
     Masc
    20.00
    節
    19.00
    lett
    18.00
    蛊
    17.75
    荼
    17.63
    脂
    17.25
     Vista
    17.13
     Elliot
    16.88
    歹
    16.88
    Activations Density 0.995%

    No Known Activations