© 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. 15042
    Prev
    Next
    INDEX
    Explanations

    list number

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

    No Comments

    Negative Logits
    -v
    -19.13
    V
    -18.25
    v
    -17.75
    BV
    -17.38
    iv
    -17.38
     PVC
    -17.13
     v
    -17.00
    VISION
    -17.00
    vision
    -16.88
    bv
    -16.88
    POSITIVE LOGITS
    �
    19.75
    がら
    19.00
     Jelly
    18.88
    alen
    18.50
    亳
    18.38
    镝
    17.50
     rake
    17.38
    吉他
    17.25
    angel
    16.88
    elah
    16.88
    Activations Density 0.008%

    No Known Activations

    This feature has no known activations.