© 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. 2210
    Prev
    Next
    INDEX
    Explanations

    say "abs"

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

    No Comments

    Negative Logits
     dat
    -19.25
    策略
    -17.63
    打法
    -17.50
     PROCUREMENT
    -17.38
    (reg
    -17.25
    策
    -16.63
     strategy
    -16.50
    ret
    -16.13
    Dat
    -15.38
     retiring
    -15.31
    POSITIVE LOGITS
    abs
    39.50
     abs
    38.50
     Abs
    37.00
    Abs
    36.25
    (abs
    34.75
    .abs
    34.50
    _abs
    33.00
    吸收
    33.00
    -abs
    31.75
     absorption
    31.50
    Activations Density 0.094%

    No Known Activations