© 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. 1504
    Prev
    Next
    INDEX
    Explanations

    [sensory] => [sensory]

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

    No Comments

    Negative Logits
     nerve
    -20.38
    Rail
    -18.88
    神经
    -17.13
    pillar
    -17.00
    odb
    -16.63
    江北
    -16.38
     nerves
    -16.13
     labor
    -16.13
    NAL
    -15.81
    sensor
    -15.63
    POSITIVE LOGITS
    伽
    18.00
     Γ
    17.25
     medications
    16.50
     Medic
    16.38
     Meditation
    15.75
    med
    15.50
    atomic
    15.44
    地中海
    15.44
     Atlas
    15.38
     medication
    15.06
    Activations Density 0.084%

    No Known Activations