© 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. 2541
    Prev
    Next
    INDEX
    Explanations

    say colon

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

    No Comments

    Negative Logits
    eq
    -18.63
    (rec
    -18.13
     ter
    -18.00
    厩
    -17.88
     poly
    -17.75
    _ter
    -17.38
    req
    -16.88
    终端
    -16.38
     eq
    -16.00
    (poly
    -16.00
    POSITIVE LOGITS
    冒
    45.00
     Col
    29.38
     col
    28.75
     colon
    28.75
    Col
    28.63
    col
    28.00
     Colon
    27.38
    .Col
    26.50
     COL
    26.50
    COL
    26.50
    Activations Density 0.019%

    No Known Activations