© 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. 3001
    Prev
    Next
    INDEX
    Explanations

    say "auth"

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

    No Comments

    Negative Logits
     TERMIN
    -17.63
     Miranda
    -16.38
     strips
    -16.25
    Mir
    -16.25
    _ter
    -16.00
    eping
    -15.69
     hexadecimal
    -15.63
    Ter
    -15.50
     INC
    -15.25
    вар
    -15.25
    POSITIVE LOGITS
     auth
    42.75
     Auth
    38.25
    Auth
    35.00
    auth
    34.50
    .auth
    34.25
    	auth
    34.25
    _auth
    29.75
    (auth
    27.13
     doc
    26.50
    /auth
    25.00
    Activations Density 0.019%

    No Known Activations