© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 3046
    Prev
    Next
    INDEX
    Explanations

    say ert

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

    No Comments

    Negative Logits
    :str
    -18.88
    甲方
    -18.75
     Meth
    -18.75
     Gener
    -17.75
     Str
    -17.38
     Arr
    -17.38
    Cap
    -17.25
     cap
    -17.25
    (annotation
    -17.13
    .gener
    -16.88
    POSITIVE LOGITS
    ert
    43.25
     cert
    41.75
     Cert
    40.75
    (cert
    40.75
    ERT
    38.50
    .cert
    38.50
    cert
    38.25
    Cert
    37.75
     Bert
    37.25
    _cert
    36.00
    Activations Density 0.170%

    No Known Activations