© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 821
    Prev
    Next
    INDEX
    Explanations

    say cpu

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

    No Comments

    Negative Logits
     Cancer
    -20.63
    癌
    -20.13
     cancers
    -18.88
    致癌
    -18.88
    .po
    -18.88
     cancer
    -18.88
     tumors
    -18.38
    郅
    -18.38
    癌症
    -18.38
     carcin
    -18.25
    POSITIVE LOGITS
     CPU
    36.25
     cpu
    35.50
    CPU
    34.00
    cpu
    32.75
    (cpu
    31.50
    _CPU
    30.63
     CPUs
    30.25
     Intel
    30.00
    /cpu
    29.13
    	cpu
    28.88
    Activations Density 0.209%

    No Known Activations