© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2028
    Prev
    Next
    INDEX
    Explanations

    writing

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

    No Comments

    Negative Logits
     writing
    -55.50
     Writing
    -53.25
    写
    -50.50
    写作
    -50.00
    Writing
    -49.25
     write
    -48.25
    write
    -47.25
    Write
    -47.00
     Write
    -47.00
     written
    -45.75
    POSITIVE LOGITS
     UUID
    16.25
    电气
    16.13
    海岛
    15.88
    esar
    14.63
     arp
    14.63
    -Ta
    14.00
    _epsilon
    13.31
     Ocean
    13.31
    Ocean
    13.25
    uhn
    13.19
    Activations Density 0.292%

    No Known Activations