© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14957
    Prev
    Next
    INDEX
    Explanations

    say names

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

    No Comments

    Negative Logits
    zt
    -20.25
     Zodiac
    -17.63
    zte
    -17.13
    óst
    -17.00
    酂
    -16.88
    zf
    -16.63
     zza
    -16.13
    zial
    -16.00
    encil
    -15.69
     Mediterr
    -15.56
    POSITIVE LOGITS
    黑马
    19.75
     Kimber
    19.63
    irk
    19.00
    奚
    18.38
    kom
    18.38
     Haw
    18.25
    hammer
    18.25
    ohn
    17.88
    ham
    17.63
     Hawks
    17.63
    Activations Density 0.598%

    No Known Activations