© 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. 2465
    Prev
    Next
    INDEX
    Explanations

    say "mul" words

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

    No Comments

    Negative Logits
    _pet
    -18.00
    范
    -16.63
    位
    -16.25
     Pet
    -16.00
     pet
    -15.75
    pet
    -15.50
    =obj
    -15.44
    [obj
    -15.06
    Cert
    -14.38
    cert
    -14.31
    POSITIVE LOGITS
     Mult
    55.50
    Mult
    55.00
     mult
    55.00
    mult
    54.75
    .mult
    45.75
    _mult
    44.50
    -mult
    43.50
     multis
    40.25
     mul
    40.00
     Mul
    40.00
    Activations Density 0.153%

    No Known Activations