© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14690
    Prev
    Next
    INDEX
    Explanations

    number one

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

    No Comments

    Negative Logits
     Porno
    -19.50
    кова
    -17.88
     Siri
    -17.75
    .star
    -17.50
     skype
    -17.00
    湓
    -16.88
    ��
    -16.88
    adera
    -16.75
    estar
    -16.75
    /star
    -16.63
    POSITIVE LOGITS
    −
    14.50
    野
    14.00
    对企业
    13.94
    articles
    13.50
     Exercises
    13.00
    工地
    12.31
    tn
    12.25
    pass
    12.19
     discontin
    12.19
    遗留
    12.13
    Activations Density 0.121%

    No Known Activations