© 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. 2709
    Prev
    Next
    INDEX
    Explanations

    father

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

    No Comments

    Negative Logits
    互
    -20.13
    erot
    -17.25
     Mut
    -17.00
    mut
    -16.63
    Trait
    -15.88
    (ret
    -15.63
     mutant
    -15.31
    (mut
    -14.75
    Mut
    -14.63
     terminator
    -14.63
    POSITIVE LOGITS
    爸爸
    61.50
    妈妈
    43.75
    爸爸妈妈
    39.25
    媽媽
    36.75
     dad
    36.75
     Dad
    35.75
    パパ
    33.00
    (src
    32.75
    eq
    31.13
     src
    31.00
    Activations Density 0.054%

    No Known Activations