© 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. 14872
    Prev
    Next
    INDEX
    Explanations

    [F] => [F]

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

    No Comments

    Negative Logits
    trs
    -14.00
    REN
    -13.25
    MLS
    -13.13
    /fw
    -12.94
    /mm
    -12.94
    (fc
    -12.81
    ment
    -12.69
     Hashtable
    -12.56
     Pan
    -12.38
    -extra
    -12.38
    POSITIVE LOGITS
     babel
    21.00
    ivas
    19.88
     sok
    19.13
     Lov
    18.75
    Soup
    18.50
    andle
    18.50
     dope
    18.13
     Copp
    17.50
     aph
    17.50
     sock
    17.25
    Activations Density 0.009%

    No Known Activations