© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15174
    Prev
    Next
    INDEX
    Explanations

    say digits

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

    No Comments

    Negative Logits
    ela
    -17.00
    及相关
    -16.63
    策
    -16.25
    健
    -15.88
    ered
    -15.69
    ertest
    -15.63
    Prov
    -15.56
    erez
    -15.44
    及以上
    -15.25
    ypy
    -15.19
    POSITIVE LOGITS
    uthor
    15.44
    牖
    15.19
    flu
    14.50
    uteur
    14.38
    losure
    14.38
    fluence
    13.94
    uffman
    13.31
    OND
    13.31
     Closure
    12.88
    DataURL
    12.75
    Activations Density 0.045%

    No Known Activations