© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15525
    Prev
    Next
    INDEX
    Explanations

    say con

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

    No Comments

    Negative Logits
    直通车
    -19.00
    /pro
    -18.75
    (pr
    -18.38
    ilib
    -18.25
    .pr
    -17.63
     wildfire
    -17.63
     Pr
    -17.50
    /pr
    -17.38
    猪肉
    -17.38
    _pr
    -17.25
    POSITIVE LOGITS
    -con
    29.63
    con
    28.13
     Con
    28.00
     conv
    27.75
    Con
    26.50
    _conv
    26.00
     Conv
    25.88
    CON
    25.75
    .con
    25.50
    .Con
    25.50
    Activations Density 3.502%

    No Known Activations