© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15104
    Prev
    Next
    INDEX
    Explanations

    say rain

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

    No Comments

    Negative Logits
     Injectable
    -18.13
    CLK
    -17.50
    OID
    -17.25
     hasher
    -17.00
     Kazakhstan
    -16.75
    _OID
    -16.75
    _PID
    -16.38
    York
    -16.25
    Britain
    -16.00
     Kremlin
    -15.69
    POSITIVE LOGITS
    雨
    19.75
     rain
    16.25
     dense
    13.81
     rains
    13.75
     Rain
    13.50
    /Sub
    13.44
    高い
    13.38
    大雨
    13.38
    商机
    13.19
     thân
    13.19
    Activations Density 0.087%

    No Known Activations