© 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. 2204
    Prev
    Next
    INDEX
    Explanations

    情景

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

    No Comments

    Negative Logits
    pol
    -22.38
    _rep
    -21.00
    (pol
    -20.63
    Pol
    -20.50
    Rep
    -19.88
    _pol
    -19.00
    ‡
    -19.00
    保
    -19.00
     Pol
    -18.75
     pol
    -18.50
    POSITIVE LOGITS
    情景
    40.50
    情
    27.88
    的情
    24.75
    景
    23.00
    情感
    19.25
     config
    19.13
    的情感
    18.25
    SENT
    17.75
     emotion
    17.63
    情形
    17.50
    Activations Density 0.099%

    No Known Activations