© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14378
    Prev
    Next
    INDEX
    Explanations

    say }

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

    No Comments

    Negative Logits
    Stripe
    -18.75
    wipe
    -17.75
     WV
    -17.63
    lée
    -16.88
    _vue
    -16.88
    wij
    -16.88
    će
    -16.63
    inality
    -16.50
    ве
    -16.50
    洗衣机
    -16.38
    POSITIVE LOGITS
    engu
    14.25
    严格落实
    13.63
     distrib
    13.50
    enna
    13.13
     subt
    12.81
    tern
    12.44
    一定能
    12.31
     services
    12.19
    荫
    12.19
     distributions
    12.06
    Activations Density 0.030%

    No Known Activations