© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2132
    Prev
    Next
    INDEX
    Explanations

    colon

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

    No Comments

    Negative Logits
    想念
    -17.88
    =req
    -17.75
    (tmp
    -16.38
     Addr
    -16.38
    (req
    -16.25
     req
    -15.56
    .dat
    -15.44
    _tmp
    -15.31
     {{{
    -15.13
     Herz
    -15.06
    POSITIVE LOGITS
     colon
    70.50
     Colon
    64.00
    colon
    63.75
    Colon
    62.50
     col
    58.50
    col
    57.50
    (col
    56.75
     colony
    55.25
    殖民
    54.75
    Col
    54.00
    Activations Density 0.273%

    No Known Activations