© 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. 2862
    Prev
    Next
    INDEX
    Explanations

    three-letter abbreviations

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

    No Comments

    Negative Logits
     DER
    -23.25
    DER
    -21.25
     deriv
    -20.25
     der
    -19.38
     CTRL
    -19.25
    _der
    -19.00
    deriv
    -18.50
     derivatives
    -17.88
    CTRL
    -17.25
     Philosophy
    -17.13
    POSITIVE LOGITS
     Col
    35.50
    Col
    28.38
     Mer
    21.13
     Seg
    21.13
     Res
    20.88
     col
    20.00
    Res
    19.25
     Pen
    18.75
     Tab
    18.63
     res
    18.25
    Activations Density 0.014%

    No Known Activations