© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2789
    Prev
    Next
    INDEX
    Explanations

    say env

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

    No Comments

    Negative Logits
     leg
    -23.00
    腿
    -22.75
    -leg
    -20.38
     Leg
    -20.25
    leg
    -19.63
    Leg
    -19.25
     termin
    -18.00
     Serializer
    -17.88
     legs
    -17.75
    _leg
    -17.63
    POSITIVE LOGITS
    环保
    53.00
    (env
    52.00
     env
    51.00
     environmental
    50.50
     Env
    49.50
    env
    47.50
     Environmental
    47.25
    Env
    46.50
    	env
    46.50
    Environmental
    46.25
    Activations Density 0.128%

    No Known Activations