© 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. 14522
    Prev
    Next
    INDEX
    Explanations

    say "8 or 9"

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

    No Comments

    Negative Logits
    wig
    -18.25
    Spell
    -17.00
    巫
    -16.75
    铛
    -16.63
    _span
    -16.00
    (chain
    -15.88
    (ac
    -15.19
     ac
    -15.19
     Sphinx
    -15.13
    �
    -14.88
    POSITIVE LOGITS
    碛
    20.13
    岳
    18.50
    dek
    18.13
    ulk
    18.00
    ulta
    17.63
    qua
    17.13
     Klaus
    17.00
     Faul
    16.63
    clé
    16.38
    laus
    16.25
    Activations Density 0.012%

    No Known Activations