© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1305
    Prev
    Next
    INDEX
    Explanations

    say psychology

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

    No Comments

    Negative Logits
    民族
    -37.50
     ethnic
    -30.88
    少数民族
    -30.75
    民族文化
    -30.50
    ethnic
    -29.63
     Ethnic
    -27.75
     ethnicity
    -27.50
    Eth
    -24.75
    种族
    -23.00
     Eth
    -21.50
    POSITIVE LOGITS
     PS
    18.88
    psi
    18.25
    _ps
    17.75
     psychology
    17.63
     Psychology
    17.50
    画
    17.50
    心理
    17.13
    Gun
    17.00
    ball
    17.00
    ps
    17.00
    Activations Density 0.111%

    No Known Activations