© 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. 2333
    Prev
    Next
    INDEX
    Explanations

    say "sen" words

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

    No Comments

    Negative Logits
    hex
    -21.88
     Hex
    -19.63
     HEX
    -19.38
    Hex
    -19.00
    Mir
    -18.63
     hex
    -18.50
    (hex
    -17.88
    Meg
    -17.50
    mir
    -17.38
    meg
    -17.25
    POSITIVE LOGITS
     Sen
    72.00
    Sen
    67.50
     sen
    65.00
    sen
    54.75
     SEN
    47.25
     seniors
    39.75
     Sens
    37.00
     Sent
    36.75
    SENS
    35.50
     senator
    35.00
    Activations Density 0.071%

    No Known Activations