© 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. 2271
    Prev
    Next
    INDEX
    Explanations

    say "history"

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

    No Comments

    Negative Logits
     modal
    -18.50
    ��
    -18.00
    (mod
    -17.63
    modx
    -17.13
    elic
    -17.13
    ���
    -16.88
    modal
    -16.75
    otomy
    -15.81
    噼
    -15.69
    emo
    -15.31
    POSITIVE LOGITS
    史
    54.00
     hist
    47.50
    Hist
    40.50
     Hist
    39.75
    hist
    37.25
    (hist
    37.00
    .hist
    33.50
    _hist
    33.25
     histogram
    30.38
     Histogram
    29.00
    Activations Density 0.115%

    No Known Activations