© 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. 15304
    Prev
    Next
    INDEX
    Explanations

    say length units

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

    No Comments

    Negative Logits
     IDX
    -15.88
    婊
    -15.75
    ATCH
    -15.13
     CActive
    -15.13
    去买
    -14.75
    拿来
    -14.50
    成为一名
    -14.31
    (PHP
    -14.31
    _OBJC
    -14.25
    ModelIndex
    -14.19
    POSITIVE LOGITS
    e
    19.75
    met
    17.13
    Meter
    15.00
    l
    14.81
     kilometres
    14.75
     metres
    14.69
     met
    14.63
    ede
    14.06
    KN
    13.88
     meter
    13.75
    Activations Density 0.068%

    No Known Activations