© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14393
    Prev
    Next
    INDEX
    Explanations

    say 思考

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

    No Comments

    Negative Logits
    仓
    -21.38
    reed
    -17.25
    涣
    -16.25
    pled
    -16.13
    Tweet
    -15.75
    nev
    -15.75
    svn
    -15.69
    CUS
    -15.50
    丛
    -15.50
    REV
    -15.44
    POSITIVE LOGITS
    舣
    15.69
    oga
    14.50
    enting
    14.44
     conjug
    14.13
     DAMAGE
    13.88
    pheric
    13.88
    env
    13.63
     FORCE
    13.50
     Force
    13.31
    engine
    12.94
    Activations Density 0.900%

    No Known Activations