© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15336
    Prev
    Next
    INDEX
    Explanations

    say S

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

    No Comments

    Negative Logits
     S
    -34.75
    _s
    -31.13
    -s
    -30.88
    S
    -29.25
    	S
    -28.88
    -S
    -28.38
     s
    -27.63
    Ｓ
    -27.63
    _S
    -27.50
    	s
    -27.50
    POSITIVE LOGITS
    чив
    18.00
    燃
    12.75
    -char
    12.44
    岐
    12.00
    beg
    12.00
    .ng
    12.00
    坊
    11.94
    NES
    11.88
     lat
    11.81
     ка
    11.81
    Activations Density 0.374%

    No Known Activations