© 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. 14736
    Prev
    Next
    INDEX
    Explanations

    say 0

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

    No Comments

    Negative Logits
     Steele
    -18.63
     Collins
    -17.38
     toll
    -17.38
    (coll
    -17.13
    _COLL
    -16.50
    coll
    -16.25
    .pose
    -16.13
    (pol
    -16.13
    Pose
    -15.81
     Cabr
    -15.75
    POSITIVE LOGITS
    icky
    20.50
    اش
    17.75
    anky
    17.50
    empt
    16.63
    esh
    16.63
    /Internal
    16.25
    slick
    16.00
    ahn
    16.00
    bcd
    15.88
    untime
    15.19
    Activations Density 0.040%

    No Known Activations