© 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. 2117
    Prev
    Next
    INDEX
    Explanations

    say ber

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

    No Comments

    Negative Logits
     Ref
    -19.50
     leg
    -19.00
    -ref
    -18.00
    /ref
    -17.88
     Lat
    -17.75
    Qual
    -17.25
     LEG
    -17.13
    -leg
    -17.13
     ref
    -17.00
    _leg
    -16.88
    POSITIVE LOGITS
    Ber
    40.25
     Ber
    38.50
     ber
    36.50
    伯
    36.25
    ber
    36.25
    _ber
    33.50
     BER
    31.00
     btn
    28.50
    百
    27.38
     buf
    27.00
    Activations Density 0.201%

    No Known Activations