© 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. 1087
    Prev
    Next
    INDEX
    Explanations

    say letter

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

    No Comments

    Negative Logits
    カル
    -29.00
    Court
    -27.75
     circuits
    -27.75
    𝐶
    -27.38
     Culture
    -26.63
    董
    -26.63
     CPS
    -26.50
    Ｃ
    -26.38
    文化
    -26.25
    CPP
    -26.13
    POSITIVE LOGITS
     cont
    14.94
    Di
    14.31
    ñe
    13.75
     kont
    13.31
     Phonetic
    13.25
    ья
    13.06
    iac
    13.00
     Petite
    12.88
     Di
    12.31
    ḍ
    12.25
    Activations Density 0.741%

    No Known Activations