© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14760
    Prev
    Next
    INDEX
    Explanations

    say measurement units

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

    No Comments

    Negative Logits
    ín
    -22.38
    inch
    -21.00
    IN
    -20.88
    icho
    -20.63
    inan
    -20.38
    Indented
    -20.38
    inke
    -20.25
    İN
    -20.13
    INAL
    -20.00
    in
    -19.88
    POSITIVE LOGITS
     K
    14.25
    ry
    13.88
    kest
    13.63
    pered
    13.06
     Bates
    12.81
    -K
    12.69
    -makers
    12.69
    tery
    12.63
    华丽
    12.38
    بط
    12.25
    Activations Density 0.043%

    No Known Activations