© 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. 15766
    Prev
    Next
    INDEX
    Explanations

    say evaluation adjectives

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

    No Comments

    Negative Logits
    盗
    -18.75
     Gloss
    -17.63
    -install
    -17.13
     Gow
    -16.63
    _skills
    -16.38
    ILLS
    -16.00
    ills
    -15.69
     IPs
    -15.63
    etty
    -15.56
    盗窃
    -15.38
    POSITIVE LOGITS
    .bundle
    16.25
     parti
    15.81
    公示
    15.63
    蒴
    15.13
    彪
    15.06
     verification
    14.94
     announces
    14.69
     annunci
    14.63
    验证
    14.38
    公布了
    14.38
    Activations Density 0.184%

    No Known Activations