© 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. 15219
    Prev
    Next
    INDEX
    Explanations

    say 9

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

    No Comments

    Negative Logits
    打好
    -17.88
     Horny
    -17.63
     rio
    -17.63
    ター
    -17.63
    urt
    -17.38
    tering
    -17.13
     Cooke
    -17.13
    Registrar
    -16.88
    usi
    -16.88
    agger
    -16.88
    POSITIVE LOGITS
    1
    14.38
    0
    13.94
    hill
    13.63
    -care
    13.19
    KIT
    13.00
    chin
    12.94
    zza
    12.63
    ellen
    12.38
     care
    12.19
    ছ
    12.06
    Activations Density 0.003%

    No Known Activations