© 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. 2764
    Prev
    Next
    INDEX
    Explanations

    say "cond" words

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

    No Comments

    Negative Logits
    利
    -18.38
    Profit
    -17.13
    �t
    -17.00
     Profit
    -16.00
    Jer
    -15.94
    (ld
    -15.94
    nds
    -15.75
    �s
    -15.63
    Mag
    -15.63
    rem
    -14.81
    POSITIVE LOGITS
     cond
    68.00
     Cond
    61.25
    Cond
    59.25
    cond
    58.25
    (cond
    57.50
    -cond
    54.75
    .cond
    52.25
    _cond
    45.00
     condensed
    44.75
    COND
    41.50
    Activations Density 0.106%

    No Known Activations