© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 551
    Prev
    Next
    INDEX
    Explanations

    say <|im_end|>

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

    No Comments

    Negative Logits
    (mc
    -15.50
    ..↵
    -15.38
    接入
    -14.75
     fram
    -14.38
    pipeline
    -14.31
    穗
    -14.25
    	mc
    -14.13
     van
    -14.00
    gold
    -13.94
    MC
    -13.69
    POSITIVE LOGITS
    &amp
    21.13
    ---</
    20.75
    akis
    18.75
     �
    18.00
    -</
    17.88
    ⁃
    17.38
     ​
    17.38
     Serg
    17.25
    ArrayOf
    17.00
    <QString
    16.88
    Activations Density 0.021%

    No Known Activations