© 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. 16377
    Prev
    Next
    INDEX
    Explanations

    differences

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

    No Comments

    Negative Logits
    .addData
    -16.25
    ucha
    -15.38
    adox
    -14.56
     inputData
    -14.25
     Mov
    -14.13
     duplex
    -14.06
     Cous
    -14.00
    EncodingException
    -13.94
    proof
    -13.94
     resistance
    -13.94
    POSITIVE LOGITS
    arker
    17.50
    沙特
    16.00
    _CLUSTER
    15.75
    ഷ
    15.19
    _cluster
    14.88
    -cl
    14.81
    cliffe
    14.50
    марк
    14.50
    鼾
    14.50
     cluster
    14.44
    Activations Density 0.202%

    No Known Activations