© 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. 2719
    Prev
    Next
    INDEX
    Explanations

    say cons

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

    No Comments

    Negative Logits
     digit
    -20.63
    数字化
    -18.88
    _digit
    -18.63
     Digit
    -18.25
     digitally
    -17.38
    Digit
    -17.13
    _digits
    -17.13
    digit
    -16.88
     Pet
    -16.50
     Hex
    -16.13
    POSITIVE LOGITS
     cons
    87.00
     Cons
    82.00
    cons
    82.00
    Cons
    80.00
    -cons
    71.00
    .cons
    66.50
     CONS
    63.50
    _cons
    60.50
    CONS
    59.00
    .Cons
    56.25
    Activations Density 0.062%

    No Known Activations