© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1322
    Prev
    Next
    INDEX
    Explanations

    say "animal names"

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

    No Comments

    Negative Logits
    lambda
    -53.50
     lambda
    -48.50
     λ
    -47.75
    λ
    -47.50
    羊
    -45.00
    剑
    -42.00
     lamb
    -40.00
    (lambda
    -39.75
     Lambda
    -39.00
    _lambda
    -37.75
    POSITIVE LOGITS
    滨江
    21.00
    心理
    19.13
     calcium
    17.63
    教育
    17.38
     CALC
    17.25
     motors
    17.00
     psychology
    17.00
    引擎
    16.88
    的心理
    16.75
     edu
    16.50
    Activations Density 0.145%

    No Known Activations