© 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. 14514
    Prev
    Next
    INDEX
    Explanations

    [name] => 1

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

    No Comments

    Negative Logits
    Actions
    -17.88
    -actions
    -17.13
     actions
    -16.38
     Actions
    -15.88
     maps
    -15.75
    actions
    -15.31
     Action
    -14.88
     action
    -14.81
    场景
    -14.56
    畴
    -14.31
    POSITIVE LOGITS
    �
    16.13
    meer
    15.75
     Cres
    15.44
    cq
    15.13
     Ryder
    15.06
    ride
    15.06
    电解
    14.75
    etched
    14.56
    _elems
    14.44
    化的
    14.38
    Activations Density 0.195%

    No Known Activations