© 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. 15694
    Prev
    Next
    INDEX
    Explanations

    say crime

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

    No Comments

    Negative Logits
    树林
    -21.13
    树木
    -19.50
    田园
    -19.38
    bose
    -18.50
    $header
    -17.63
     Nile
    -16.75
    树叶
    -16.63
     UPLOAD
    -16.38
     trees
    -16.25
    CADE
    -16.25
    POSITIVE LOGITS
    刑
    25.13
    刑事
    24.38
    crime
    22.88
    犯罪
    22.75
     crim
    22.75
    司法
    22.50
     criminal
    22.25
     Prosecutor
    22.13
     sentencing
    22.00
     prison
    21.88
    Activations Density 0.232%

    No Known Activations