© 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. 2520
    Prev
    Next
    INDEX
    Explanations

    say "accumulation"

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

    No Comments

    Negative Logits
     modal
    -18.75
     Modal
    -18.13
     btn
    -18.13
     Tel
    -18.00
    .msg
    -17.25
    妳
    -16.88
    .modal
    -16.88
     Opt
    -16.63
    _btn
    -16.25
     tel
    -16.25
    POSITIVE LOGITS
    积
    51.00
    積
    47.25
    累积
    34.50
     accum
    34.00
    积累
    32.25
     accumulation
    31.75
     Accum
    31.00
    accum
    30.63
     accumulate
    27.50
     accumulated
    27.00
    Activations Density 0.118%

    No Known Activations