© 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. 14756
    Prev
    Next
    INDEX
    Explanations

    say "5"

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

    No Comments

    Negative Logits
    quat
    -19.75
    麓
    -19.50
     Blaze
    -18.75
    渚
    -18.75
    ampoo
    -18.38
    asString
    -18.13
     Fraser
    -17.63
    essenger
    -17.63
     Blizzard
    -17.13
    uve
    -17.13
    POSITIVE LOGITS
    OTTOM
    18.38
    ICT
    15.50
    IZER
    15.44
    殷
    14.69
    VERT
    14.69
    jen
    14.00
    0
    13.88
    ENC
    13.69
    ERT
    13.50
    HC
    13.44
    Activations Density 0.033%

    No Known Activations