© 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. 16296
    Prev
    Next
    INDEX
    Explanations

    say "factor" words

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

    No Comments

    Negative Logits
    殷
    -16.63
    ynchron
    -16.38
     watchdog
    -15.44
    稀
    -15.31
    精神文明
    -14.88
    arden
    -14.38
    Checksum
    -14.19
    种子
    -14.19
    舞蹈
    -14.06
    纪委书记
    -14.06
    POSITIVE LOGITS
    因素
    50.00
     factor
    49.50
     factors
    49.00
    _factors
    45.00
    factor
    44.75
     Factor
    44.25
     Factors
    43.00
    的因素
    42.50
    Factor
    42.25
    因子
    42.00
    Activations Density 0.335%

    No Known Activations