© 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. 15796
    Prev
    Next
    INDEX
    Explanations

    times of day

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

    No Comments

    Negative Logits
    -A
    -32.50
    А
    -31.63
    AA
    -30.00
    AO
    -29.88
    ア
    -29.38
    _aa
    -29.00
    AE
    -28.75
    阿
    -28.75
    AF
    -28.63
    ACL
    -28.63
    POSITIVE LOGITS
    蕉
    15.00
     PB
    14.81
    PB
    14.13
     TG
    13.75
     SCH
    13.44
    謇
    13.19
    lé
    12.94
     Urs
    12.88
     JP
    12.81
    UNC
    12.75
    Activations Density 3.377%

    No Known Activations