© 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. 14721
    Prev
    Next
    INDEX
    Explanations

    say digits

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

    No Comments

    Negative Logits
    aday
    -20.38
    	Py
    -19.88
    apult
    -19.75
    İN
    -19.75
    adel
    -19.63
    aroo
    -19.38
    drs
    -19.25
    inate
    -19.25
    inant
    -19.25
    irth
    -19.13
    POSITIVE LOGITS
     freaking
    13.44
     fucking
    12.38
     much
    12.25
     к
    11.88
    1
    11.81
    候
    11.75
    揭
    11.63
    著
    11.31
     k
    11.13
     vig
    11.13
    Activations Density 0.107%

    No Known Activations