© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 16322
    Prev
    Next
    INDEX
    Explanations

    say "rehab"

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

    No Comments

    Negative Logits
     pne
    -19.25
     yağ
    -18.75
    pine
    -18.25
    洋葱
    -17.25
    queen
    -17.13
    茄子
    -17.13
    ilan
    -17.00
    コピー
    -17.00
     Pir
    -17.00
    .inflate
    -16.50
    POSITIVE LOGITS
     rehab
    22.25
     Recovery
    19.88
     recovery
    19.88
    康复
    18.75
     addict
    18.38
    复发
    18.00
    戒
    17.88
     Recover
    17.75
     addiction
    17.63
     Addiction
    17.63
    Activations Density 0.163%

    No Known Activations