© 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. 1935
    Prev
    Next
    INDEX
    Explanations

    [alpha] => [beta]

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

    No Comments

    Negative Logits
     alpha
    -46.00
    alpha
    -43.25
    Alpha
    -40.75
     Alpha
    -40.25
    -alpha
    -39.00
     beta
    -39.00
    (alpha
    -37.50
     α
    -37.25
    α
    -36.75
     ALPHA
    -36.75
    POSITIVE LOGITS
    _ART
    16.13
     الفلسطين
    15.69
    DEX
    15.06
     geological
    15.06
     Embassy
    14.69
    _GE
    14.44
    看病
    14.44
     Bangladesh
    14.44
     circuit
    14.31
    urse
    14.19
    Activations Density 0.115%

    No Known Activations