© 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. 2724
    Prev
    Next
    INDEX
    Explanations

    say German

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

    No Comments

    Negative Logits
    REF
    -20.00
     ref
    -19.88
    (ref
    -19.50
    	ref
    -17.88
     Harr
    -17.13
     REF
    -17.13
    =res
    -16.88
    .ref
    -16.13
    ceptor
    -16.00
     Utt
    -15.94
    POSITIVE LOGITS
    德
    38.00
    代
    33.75
     Ger
    30.75
    Ger
    29.88
     German
    29.75
    德国
    28.38
     german
    27.75
    ger
    26.88
    German
    26.88
     ger
    26.50
    Activations Density 0.117%

    No Known Activations