© 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. 14889
    Prev
    Next
    INDEX
    Explanations

    say non‑Latin

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

    No Comments

    Negative Logits
     Broncos
    -17.38
     проб
    -15.81
    聘
    -15.69
    -du
    -15.38
     Zig
    -15.31
     Dob
    -15.13
    沾
    -15.06
     Daisy
    -15.06
     Greenville
    -14.94
     sniff
    -14.88
    POSITIVE LOGITS
    rita
    21.38
    va
    20.25
    arth
    19.38
    atha
    18.75
    REA
    18.63
    vat
    18.38
    口袋
    17.00
    еча
    17.00
    vä
    16.88
     cellul
    16.75
    Activations Density 0.828%

    No Known Activations