© 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. 3060
    Prev
    Next
    INDEX
    Explanations

    say cert

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

    No Comments

    Negative Logits
     retVal
    -20.00
    Fil
    -19.25
     Fil
    -18.63
    pos
    -18.63
    �
    -18.50
     retval
    -18.00
     DEV
    -17.50
    (retval
    -17.00
    _ARR
    -17.00
    零售
    -16.75
    POSITIVE LOGITS
    证
    50.50
     cert
    45.25
    cert
    38.50
    Cert
    37.25
    證
    37.00
     Cert
    35.75
    (cert
    35.00
     certification
    33.75
     certify
    33.25
    证书
    32.75
    Activations Density 0.065%

    No Known Activations