© 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. 865
    Prev
    Next
    INDEX
    Explanations

    say "IB"

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

    No Comments

    Negative Logits
    亳
    -22.75
     Milwaukee
    -20.50
    太原
    -20.00
    姥
    -19.63
    郓
    -19.25
    轵
    -18.13
    长春
    -18.13
     MMM
    -17.75
    虢
    -17.50
    帽
    -17.38
    POSITIVE LOGITS
     IB
    36.50
    IB
    34.75
    (ib
    31.88
     ib
    31.00
    _ib
    30.50
    (IB
    29.13
    .ib
    29.00
    ib
    28.75
     Ib
    28.75
    _IB
    26.50
    Activations Density 0.041%

    No Known Activations