© 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. 2395
    Prev
    Next
    INDEX
    Explanations

    say "char" words

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

    No Comments

    Negative Logits
    Perm
    -19.75
     Per
    -18.25
     Perm
    -17.25
    叙
    -17.25
    Per
    -17.25
    _per
    -17.13
     perm
    -16.38
    精子
    -16.25
     permutation
    -16.00
     Err
    -15.50
    POSITIVE LOGITS
     charity
    49.00
     Charity
    44.00
    char
    41.75
     charities
    40.75
    慈善
    40.50
     char
    40.00
    Char
    38.00
     charitable
    37.50
    (char
    36.75
    ,char
    36.25
    Activations Density 0.043%

    No Known Activations