© 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. 14519
    Prev
    Next
    INDEX
    Explanations

    [title] => [surname]

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

    No Comments

    Negative Logits
    节
    -20.88
     Masc
    -20.00
    節
    -19.63
    lett
    -18.75
    荼
    -18.38
    脂
    -18.25
    蛊
    -18.13
    ikt
    -17.63
    歹
    -17.63
    icol
    -17.50
    POSITIVE LOGITS
     Haj
    18.25
    hare
    18.00
    aina
    17.75
    rabbit
    17.63
     prisoner
    17.50
     rabbits
    17.38
     hydrogen
    16.88
    akis
    16.88
     hare
    16.63
    昆仑
    16.25
    Activations Density 1.000%

    No Known Activations