© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 16232
    Prev
    Next
    INDEX
    Explanations

    non‑Latin characters

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

    No Comments

    Negative Logits
     SI
    -17.25
    Pl
    -17.13
    .ci
    -16.63
    rai
    -16.63
     Hanna
    -16.50
    жи
    -16.50
     Pl
    -16.00
    Convention
    -15.88
    _SI
    -15.69
    .PL
    -15.63
    POSITIVE LOGITS
    邴
    19.88
    oref
    19.25
    疏导
    18.50
     recharge
    18.38
    派遣
    17.88
    劳务派遣
    17.63
    泔
    17.63
    -stream
    17.63
     Spokane
    17.50
     perm
    17.13
    Activations Density 0.575%

    No Known Activations