© 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. 2144
    Prev
    Next
    INDEX
    Explanations

    say Hel words

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

    No Comments

    Negative Logits
    Pres
    -18.88
     Pres
    -18.50
    _pres
    -17.88
    digit
    -17.50
     Emin
    -17.13
     Straw
    -17.13
     Preserve
    -16.88
    .pres
    -16.25
    師
    -16.13
     pres
    -16.00
    POSITIVE LOGITS
    Hel
    76.00
     Hel
    73.50
     hel
    68.50
    hel
    56.00
     HEL
    47.00
    _HEL
    40.50
     helicopter
    39.50
     Helena
    36.00
    HEL
    35.00
     helicopters
    33.75
    Activations Density 0.094%

    No Known Activations