© 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. 2182
    Prev
    Next
    INDEX
    Explanations

    say "des"

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

    No Comments

    Negative Logits
     emitting
    -16.13
     rad
    -15.44
     BTN
    -15.25
     Certified
    -14.75
    enstein
    -14.69
    -ret
    -14.69
     emit
    -14.63
    arged
    -14.31
    INCT
    -14.31
     Utt
    -14.19
    POSITIVE LOGITS
     des
    83.00
     Des
    72.00
    Des
    71.50
    -des
    66.50
    des
    66.00
    (des
    64.50
    	des
    63.50
    .des
    62.25
    _des
    58.75
     DES
    57.75
    Activations Density 0.161%

    No Known Activations