© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15069
    Prev
    Next
    INDEX
    Explanations

    Method 2 – TOKENS_AFTER_MAX_ACTIVATING_TOKEN are almost exclusively “8” or “9”. 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
    スト
    -13.88
    향
    -13.88
    -plugins
    -13.88
    *T
    -13.69
    *p
    -13.56
    .twitch
    -13.50
     col
    -13.44
    执
    -13.31
     Trot
    -13.25
    史
    -13.25
    POSITIVE LOGITS
    rea
    23.13
    eka
    18.88
    xa
    18.88
    inge
    17.88
    iae
    17.75
    esa
    17.25
    rear
    17.00
    rie
    16.88
    enda
    16.50
    embre
    16.50
    Activations Density 0.020%

    No Known Activations