© 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. 2057
    Prev
    Next
    INDEX
    Explanations

    say "pole"

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

    No Comments

    Negative Logits
    emet
    -17.00
    (Msg
    -16.13
     mut
    -16.13
    $config
    -15.56
     Cert
    -15.50
     resetting
    -15.38
    =req
    -15.31
    给宝宝
    -15.31
    (det
    -15.25
    hower
    -15.13
    POSITIVE LOGITS
     pole
    64.50
     Pole
    60.00
    pole
    54.50
     poles
    50.50
     pol
    46.25
    Pol
    46.25
     Pol
    45.50
    pol
    45.00
    极
    43.25
    (pol
    41.25
    Activations Density 0.048%

    No Known Activations