© 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. 1602
    Prev
    Next
    INDEX
    Explanations

    heat

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

    No Comments

    Negative Logits
     heat
    -32.75
     Heat
    -30.88
    Heat
    -29.88
    heat
    -29.50
     heats
    -29.38
     heating
    -28.38
    _heat
    -27.13
    热
    -26.88
     Heating
    -26.50
    _HE
    -25.00
    POSITIVE LOGITS
     American
    17.75
    α
    17.50
     Americ
    17.00
    canvas
    16.50
    mlin
    16.38
    alpha
    15.38
    American
    15.38
    美国
    15.13
    python
    14.88
    (canvas
    14.75
    Activations Density 0.092%

    No Known Activations